This MCP server provides tools for KYB, due diligence, and B2G sales intelligence on Brazilian companies and public procurement, with paid tools settling automatically in USDC on Base (via x402 protocol).
Company Registry & Due Diligence
Basic company lookup: Retrieve legal name, status, CNAE activities, address, and incorporation date by CNPJ ($0.01)
Full due diligence: Everything above plus partners/shareholders (QSA) and sanction checks (CEIS/CNEP) ($0.10)
Regulatory risk screening: Screen against federal debarment (CEIS), anti-corruption (CNEP), leniency agreements, and forced-labor registers — returns a verdict and 0–100 risk score ($0.03)
Company search & segmentation: Search ~28M active companies by CNAE, state/city, size, MEI status, name, registration date, and contact info availability ($0.05/page)
Document Validation & Decoding
CNPJ validation: Check-digit and format validation — free
Batch document validation: Validate up to 100 Brazilian identifiers (CPF, CNPJ, PIS, license plates, Pix keys) ($0.002)
NF-e key decoding: Decode a 44-digit electronic invoice access key to extract issuer CNPJ, state, date, and invoice number ($0.005)
Boleto decoding: Decode a boleto digitable line (47–48 digits) to get bank, amount, due date, and validity ($0.005)
Postal Code Lookup
CEP lookup: Enriched lookup returning full address, IBGE city code, and coordinates when available ($0.005)
Public Tenders (PNCP / Compras.gov.br)
Decode tender ID: Offline decode of a Compras.gov.br 17-digit tender ID into UASG, modality, number, and year ($0.005)
Resolve tender reference: Resolve any tender reference (17-digit ID, URL, or PNCP control number) to canonical PNCP coordinates and a summary ($0.02)
Get tender header: Full header including object, modality, status, estimated value, dates, and buyer info ($0.01)
Get tender items: All line items with quantities, maximum prices, units, and SME-exclusive (ME/EPP) flags ($0.03)
Get tender documents: List document download URIs (edital PDFs, ZIPs) ($0.01)
Search tenders: Keyword search across Brazilian public procurement tenders via PNCP ($0.05)
Paid tools are charged only on success; a wallet private key must be configured.
Allows validation of Pix keys (Brazilian instant payment identifiers) as part of batch document validation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@brdata-mcp run full due diligence on CNPJ 00.000.000/0001-91"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server for Brazilian company & public-procurement data, for agent harnesses (Claude Code, Claude Desktop, …). It covers: CNPJ company registry lookup (basic + full due-diligence), company search/discovery across ~28M active companies by filters (CNAE activity, state/city, size, MEI, name), public tenders / licitações via PNCP (decode Compras.gov.br IDs, resolve, header, line items, edital documents, keyword search), NF-e & boleto decoding, CEP lookup, and batch document validation — for KYB, due diligence, and B2G (public-sector) sales intelligence.
Paid tools automatically settle the underlying x402-protected HTTP endpoints in USDC
on Base or Solana using a wallet you configure; a call is charged only on success. Configure a
Base wallet (EVM_PRIVATE_KEY), a Solana wallet (SOLANA_PRIVATE_KEY), or both — the x402 layer
settles on whichever rail the server's 402 challenge advertises.
Tool | Endpoint | Price | Description |
|
| $0.005 | Consolidated registry profile |
|
| $0.03 | + partners (QSA) + sanctions |
|
| $0.015 | Regulatory risk & compliance screen across 5 federal registries: debarment (CEIS), anti-corruption (CNEP), impeded non-profits (CEPIM), leniency & forced-labor register ("Lista Suja", MTE) → verdict + 0–100 score + per-source |
|
| $0.005 | NF-e/NFC-e 44-digit access-key decoder |
|
| $0.005 | Boleto digitable-line decoder |
|
| $0.001 | Batch validate CPF/CNPJ/PIS/plate/Pix (≤100) |
|
| $0.002 | Enriched postal-code lookup |
|
| $0.015/page | Search & segment active companies by CNAE/location/size/age/name |
|
| $0.005 | Offline decode of a Compras.gov.br 17-digit tender id |
|
| $0.02 | Resolve any tender reference (id/URL/control number) to PNCP + summary |
|
| $0.01 | Full tender header (PNCP) |
|
| $0.03 | All tender items + ME/EPP-exclusive flags |
|
| $0.01 | Tender document URIs (no PDF download) |
|
| $0.05 | Search public tenders (PNCP) by keyword |
|
| free | Single CNPJ check-digit validation |
search_companies requires the Worker to have the Phase 2 database configured (Hyperdrive);
otherwise it returns a 503 (and no payment is charged). MEI contact data is redacted (LGPD).
Related MCP server: cnpjaberto
Environment variables:
Var | Required | Default | Meaning |
| no |
| Base URL of a brdata Worker (defaults to the hosted production API) |
| for paid tools (Base) | — |
|
| for paid tools (Solana) | — | base58 or JSON-array secret key of the paying Solana wallet (holds USDC). Configure this and/or |
| no | public RPC | Optional Solana RPC override used to build the payment (e.g. a Helius URL) |
| no |
|
|
EVM_PRIVATE_KEY controls real funds. Anything that can read this process'
environment (or the MCP config file) can spend from that wallet.
Use a dedicated wallet with a small balance, funded only with what you're willing to auto-spend. Never a personal or treasury key.
On testnet (base-sepolia) use test USDC only.
The key is read from the environment; it is never sent anywhere except to sign
x402 payment authorizations for BRDATA_BASE_URL.
Add to your mcpServers configuration:
{
"mcpServers": {
"brdata": {
"command": "npx",
"args": ["-y", "brdata-mcp"],
"env": {
"EVM_PRIVATE_KEY": "0x<dedicated-wallet-key-with-USDC>"
}
}
}
}For local development against wrangler dev, point BRDATA_BASE_URL at
http://localhost:8787 and use X402_NETWORK=base-sepolia with a testnet wallet.
If you run from source instead of npm, use:
{
"mcpServers": {
"brdata": {
"command": "node",
"args": ["/absolute/path/to/packages/brdata-mcp/dist/index.js"],
"env": { "BRDATA_BASE_URL": "http://localhost:8787", "EVM_PRIVATE_KEY": "0x...", "X402_NETWORK": "base-sepolia" }
}
}
}"Use brdata to run full due diligence on CNPJ 00.000.000/0001-91."
The agent calls lookup_company_full, which pays $0.03 in USDC and returns the
consolidated English profile with partners and sanction checks.
pnpm install
pnpm run build # emits dist/
pnpm run typecheck
# publish (see checklist in the main repo README before doing this):
npm publish --access publicMIT
Decode a Brazilian boleto linha digitável (47 or 48 digits): bank, amount, due date, validity. Paid ($0.005).
| Name | Required | Description | Default |
|---|---|---|---|
| digitable_line | Yes | Boleto digitable line (47 or 48 digits). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so description carries full burden. Mentions paid cost ($0.005) which is a behavioral trait, but does not disclose read-only nature, error handling, or other side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence efficiently conveys purpose, extracted fields, and cost. Lacks any waste, but could be slightly improved by mentioning output format or errors.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description lists returned fields, which is helpful. However, it omits details on response format, error conditions, or interaction with other tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description repeats the schema's parameter description without adding new semantic information about the digitable line beyond what is already provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool decodes a Brazilian boleto digitable line and lists extracted fields (bank, amount, due date, validity). Distinguishes from siblings that handle different document types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when/when-not guidance, but the context (sibling tools with different purposes) implies this is for boleto lines only. Lacks alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Decode a 44-digit Brazilian electronic invoice (NF-e/NFC-e) access key: issuer CNPJ, state, emission date, invoice number, model. Paid ($0.005).
| Name | Required | Description | Default |
|---|---|---|---|
| access_key | Yes | 44-digit NF-e access key. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions a cost ($0.005) and what fields are extracted, which adds some behavioral context. However, it does not disclose any error conditions, rate limits, or side effects. For a read-only decoding tool, this is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two concise sentences. The first sentence states the action and key outputs; the second adds cost context. It is front-loaded with the most important information and contains no redundant or irrelevant content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has only one parameter, no output schema, and no annotations, the description covers the essential aspects: input format, extracted fields, and cost. It lacks explicit return format details, but listing the fields provides reasonable completeness for a simple decoding tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (the sole parameter access_key is described as '44-digit NF-e access key'). The description does not add extra meaning for the parameter beyond what the schema already provides. Baseline score of 3 applies per rules.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it decodes a 44-digit Brazilian NF-e/NFC-e access key and lists specific extracted fields (issuer CNPJ, state, emission date, invoice number, model). This clearly distinguishes it from sibling tools like decode_boleto or decode_tender_id, which serve different document types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for NF-e keys but does not explicitly state when to use this tool instead of alternatives. No when-not or exclusion criteria are provided. Given sibling tools cover different document types, the context is clear but lacks explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Offline decode of a Compras.gov.br 17-digit tender id (UASG + modality + number + year), with the modality name in English. Paid ($0.005).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | 17-digit Compras.gov.br id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'offline' and cost ($0.005), but does not disclose whether the tool is read-only, side effects, rate limits, or authentication requirements, leaving significant gaps in behavioral understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that conveys essential information (offline, input format, cost). It is front-loaded and avoids fluff, though it could be slightly more structured with bullet points for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description explains the input structure and mentions the modality name as output. However, it does not fully describe the output format (e.g., object keys) or any error behavior, leaving some ambiguity for agents.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% but the description adds meaning beyond the schema by explaining the id structure (UASG + modality + number + year) and indicating the output includes the modality name in English. This helps the agent understand input specifics and expected output.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool decodes a 17-digit Compras.gov.br tender id into components (UASG, modality, number, year) and provides the modality name in English. It distinguishes itself from siblings like decode_boleto or decode_nfe_key by specifying the exact input and output.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when you have a tender ID and need its decoded components, but does not explicitly state when to use versus alternatives like get_tender or resolve_tender, nor does it mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full header of a Brazilian public tender by PNCP coordinates: object, modality, status, estimated value, opening/closing dates, buyer, price-registration flag. Paid ($0.01).
| Name | Required | Description | Default |
|---|---|---|---|
| seq | Yes | PNCP sequential (NOT the Compras.gov.br number). | |
| cnpj | Yes | Buyer agency CNPJ (14 digits). | |
| year | Yes | Tender year (>= 2021). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the cost ($0.01) but does not mention other behaviors such as rate limits, authentication requirements, or error handling. The lack of output schema also leaves the response structure ambiguous.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the purpose and lists included fields. No redundant or irrelevant text. Every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the three required parameters and no output schema, the description covers the main inputs and output scope. However, it lacks details on error handling, response format, or prerequisites. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with clear descriptions for each parameter. The tool description adds context about 'PNCP coordinates' but does not significantly enhance the parameter understanding beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves the 'full header' of a Brazilian public tender by PNCP coordinates, listing specific fields (object, modality, status, estimated value, dates, buyer, flag). This distinguishes it from sibling tools like get_tender_documents and get_tender_items which handle sub-parts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives like search_tenders or resolve_tender. It only implies usage by specifying the coordinates needed, but lacks when-to-use or when-not-to-use advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Document list (download URIs) of a Brazilian public tender. ZIPs usually contain the full edital PDF and item list. Metadata only — files are not fetched. Paid ($0.01).
| Name | Required | Description | Default |
|---|---|---|---|
| seq | Yes | PNCP sequential (NOT the Compras.gov.br number). | |
| cnpj | Yes | Buyer agency CNPJ (14 digits). | |
| year | Yes | Tender year (>= 2021). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full responsibility. It discloses that files are not fetched (metadata only), that ZIPs typically contain edital PDF and item list, and that there is a cost ($0.01). This covers key behavioral traits aside from authorization or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences front-load the core purpose and provide essential context without waste. Every sentence adds value: tool purpose, ZIP contents, and metadata/payment note.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no output schema, the description covers purpose, result type (URIs), content hints (ZIPs contain PDF and item list), and cost. Missing mentions of pagination or limits, but adequate for the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds no additional parameter-specific meaning beyond the schema descriptions. The payment note is a general behavioral aspect, not parameter-related.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('list') and resource ('documents of a Brazilian public tender'), and specifies it returns download URIs. It distinguishes from siblings like get_tender and get_tender_items by focusing on document URIs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no explicit guidance on when to use this tool versus its siblings. It implies usage for listing document URIs but lacks when-to-use, when-not-to-use, or alternative tool mentions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
All items of a Brazilian public tender: quantities, maximum accepted prices, units, and SME-exclusive (ME/EPP) flags. Essential for bid/no-bid analysis. Paid ($0.03).
| Name | Required | Description | Default |
|---|---|---|---|
| seq | Yes | PNCP sequential (NOT the Compras.gov.br number). | |
| cnpj | Yes | Buyer agency CNPJ (14 digits). | |
| year | Yes | Tender year (>= 2021). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses cost ($0.03) and data fields, but lacks details on authorization, rate limits, or side effects. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences convey purpose, key data, and cost. No fluff; every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description lists expected fields (quantities, prices, units, flags) but doesn't specify format (array/object) or pagination. Sufficient for a straightforward item list.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with descriptions for all 3 parameters. The description adds value by clarifying that 'seq' is the 'PNCP sequential (NOT the Compras.gov.br number)', which helps avoid confusion.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns 'All items of a Brazilian public tender' with specific fields (quantities, prices, units, SME flags). This distinguishes it from sibling tools like get_tender (header data) and search_tenders (finding tenders).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It mentions the tool is 'Essential for bid/no-bid analysis' and notes it's paid, but does not explicitly contrast with siblings or provide when/when-not criteria. Usage context is implied by the tool listing items after tender discovery.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enriched CEP lookup: full address, IBGE city code, coordinates when available. Paid ($0.005).
| Name | Required | Description | Default |
|---|---|---|---|
| cep | Yes | 8-digit Brazilian postal code (CEP). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must carry behavioral info. It discloses the cost ($0.005) and that coordinates are conditional ('when available'). The lookup nature implies a read operation, but no explicit statement on side effects or auth needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, information-dense sentence with no redundancy. Every element (enriched CEP lookup, output fields, cost) earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 1-parameter tool with no output schema, the description adequately explains what the tool returns and the cost. A minor gap is the lack of detail on when coordinates are available, but overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds no extra semantics beyond what the schema already provides ('8-digit Brazilian postal code'). Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a Brazilian postal code lookup and lists the enriched data returned: full address, IBGE city code, and coordinates when available. This distinguishes it from sibling tools like decode_boleto or lookup_company.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context implies usage for Brazilian CEP lookups. The sibling tools cover distinct entities (boléto, NF-e, company, tender), so the tool's purpose is clear. However, no explicit when-not or alternative instructions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Consolidated official registry profile of a Brazilian company by CNPJ: legal name, status, activities (CNAE), address, incorporation date. Paid ($0.01).
| Name | Required | Description | Default |
|---|---|---|---|
| cnpj | Yes | Brazilian company tax ID (CNPJ), 14 digits, with or without punctuation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description adds cost ($0.01) and indicates it's a read operation ('Consolidated registry profile'). Does not disclose potential rate limits, authentication needs, or response size. Adds some value beyond structural fields but could be more transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence efficiently conveys purpose, returned fields, and cost. No wasted words, but could be slightly more structured (e.g., bullet points).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 1 parameter, no output schema, and no annotations, the description adequately lists the returned fields (legal name, status, activities, address, incorporation date). Lacks details on error handling or data freshness, but sufficient for a basic lookup.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description of the cnpj parameter. The tool description redundantly mentions 'by CNPJ', adding no new semantics over the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool consolidates official registry profile of a Brazilian company by CNPJ, listing key fields (legal name, status, activities, address, incorporation date). This distinguishes it from siblings like lookup_company_full (likely more detailed) and screen_company_risk.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage through the word 'basic', suggesting a quick profile lookup, and mentions a cost ($0.01). However, no explicit when-not or alternative tools are named, despite having related siblings like search_companies or lookup_company_full.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full profile: everything in lookup_company plus partners/shareholders (QSA) and government sanction checks (CEIS/CNEP). Paid ($0.10).
| Name | Required | Description | Default |
|---|---|---|---|
| cnpj | Yes | Brazilian company tax ID (CNPJ), 14 digits, with or without punctuation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only discloses the paid nature ($0.10) and scope, but does not mention rate limits, error behavior, or other operational traits. For a read tool, more behavioral context would be helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, front-loading the key purpose and then adding paid detail. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter retrieval tool without output schema, the description provides essential context: scope (full profile) and cost. It is nearly complete, though it could mention output format or any limitations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description of the 'cnpj' parameter. The tool description does not add any additional parameter information beyond the schema, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides a full profile including partners/shareholders and sanction checks, distinguishing it from the sibling lookup_company. The verb 'lookup' and resource 'Brazilian company full due diligence' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use: when full profile with QSA and sanctions is needed, and mentions it is paid ($0.10). It differentiates from lookup_company by saying 'everything in lookup_company plus', but lacks explicit exclusions or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve any Brazilian public tender reference (Compras.gov.br 17-digit id or URL, PNCP URL, or control number) into canonical PNCP coordinates + a summary (object, modality, estimated value, dates). Paid ($0.02).
| Name | Required | Description | Default |
|---|---|---|---|
| reference | Yes | A 17-digit id, a Compras.gov.br/PNCP URL, or a PNCP control number (CNPJ-1-SEQ/ANO). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden. It discloses the $0.02 cost and summarizes the output structure, which is transparent for a resolver tool. Could be slightly more detailed on 'canonical PNCP coordinates'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first defines the action and inputs, second adds cost and output summary. No wasted words, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description specifies the return components (canonical PNCP coordinates, summary with fields). Complete enough for a single-parameter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The tool description restates the accepted formats, adding no new semantic information beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool resolves Brazilian public tender references into canonical PNCP coordinates with a summary, specifying accepted input formats. It distinguishes itself from siblings like 'get_tender' which fetches full tender data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied by the input formats described, but there is no explicit guidance on when not to use or alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Screen a Brazilian company by CNPJ against the federal debarment (CEIS), anti-corruption (CNEP) and leniency-agreement registries. Returns a single verdict (clear/flagged) + 0–100 risk score, each hit flagged active vs historical. The Brazilian complement that global OFAC/EU/UK/UN + PEP screens miss — a company barred by the Brazilian government comes back clean on those. Company-level public data; no CPF (LGPD). Paid ($0.03).
| Name | Required | Description | Default |
|---|---|---|---|
| cnpj | Yes | Brazilian company tax ID (CNPJ), 14 digits, with or without punctuation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the return format (verdict + 0–100 risk score, active vs historical hits), the data sources (three registries), and that it is company-level public data. It does not mention authentication or rate limits, but the read-only nature is implied. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences. The first sentence covers purpose and behavior; the second provides differentiation, limitations, and cost. It is front-loaded, concise, and every sentence adds value with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool screens against multiple registries and returns a verdict with risk scores, the description covers the essential aspects: what it screens, what it returns, how it differs from siblings, and key constraints (LGPD, cost). It does not detail the risk score calculation or output structure, but since there is no output schema, the description provides sufficient context for an agent to select and use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is only one parameter (cnpj) and the schema already fully describes it (100% coverage). The description mentions 'by CNPJ' but does not add additional semantic details beyond the schema, so baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool screens Brazilian companies by CNPJ against specific federal registries (CEIS, CNEP, leniency-agreement). It explicitly distinguishes from sibling global screening tools, noting it covers a gap global screens miss. The title and description align perfectly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use: as a complement to global OFAC/EU/UK/UN and PEP screens for Brazilian-specific risk. It also mentions limitations (no CPF due to LGPD) and cost ($0.03), helping agents decide. It does not explicitly say when not to use, but the differentiation implicitly covers that.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search active Brazilian companies by industry (CNAE prefix, main activity), location (state/city), size, age (registration date) and legal-name substring. Returns official registry data with business contact info (MEI contacts are redacted under LGPD). Cursor paginated. Paid per page ($0.05). At least one filter is required.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City name (accent/case-insensitive) or a TOM/IBGE code. | |
| cnae | No | CNAE prefixes (4-7 digits), matched on the MAIN activity. | |
| state | No | State (UF), e.g. "MS". | |
| cursor | No | Pass the previous response's next_cursor. | |
| is_mei | No | ||
| has_email | No | ||
| has_phone | No | ||
| page_size | No | Default 25, max 50. | |
| company_size | No | ||
| opened_after | No | registration_date >= YYYY-MM-DD. | |
| name_contains | No | ||
| opened_before | No | registration_date <= YYYY-MM-DD. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses pagination (cursor), cost ($0.05/page), and data redaction (LGPD for MEI contacts). However, it omits rate limits, required authentication, and the response structure, leaving some behavioral aspects uncovered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three well-structured sentences front-load the main action and key constraints. Every sentence adds essential information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 12 parameters and no output schema, the description provides a solid overview including pagination, cost, and data handling. It could elaborate on return format or error cases, but it is largely sufficient for an experienced agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 58% (7/12 params have descriptions). The description adds thematic grouping (industry, location, size, age, name) and clarifies that CNAE prefixes match on main activity and city can be name or code. This adds value but does not detail every parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches and segments active Brazilian companies using various filters. The verb 'search & segment' plus the specific resource 'active Brazilian companies' distinguishes it from single-company lookups (lookup_company) and tender searches (search_tenders).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description requires at least one filter and notes the paid-per-page cost, but does not explicitly state when to use this tool versus alternatives like lookup_company. However, the context signals and sibling names imply the difference, so the guidance is mostly clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Brazilian public procurement tenders (PNCP) by keyword. Returns normalized references (CNPJ/year/sequential, control number, PNCP URL) ready for detail lookups. Paid ($0.05).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page (default 1). | |
| query | Yes | Keyword(s), min 3 chars. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the paid nature and the returned fields but does not mention pagination behavior (the page parameter), potential result limits, or filtering by date/status. It lacks detail on what happens if the query has no results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences convey purpose, result format, and pricing. No filler or repetition. Every sentence is informative and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema, no nested objects), the description covers essential aspects: what it searches, what it returns, and cost. Minor gaps exist (pagination, result limits), but overall it is complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the two parameters (query and page), with minLength and minimum constraints documented. The description adds no extra semantic detail beyond 'by keyword' for query and no mention of page. With full schema coverage, a 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Brazilian public procurement tenders by keyword and returns normalized references (CNPJ/year/sequential, control number, PNCP URL). It distinguishes from sibling tools like get_tender, decode_tender_id, etc., which are for specific lookups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates the output is 'ready for detail lookups,' guiding the agent to use subsequent tools like get_tender. It also mentions the cost ($0.05), which is a usage consideration. However, it does not explicitly state when not to use or name alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free local check-digit/format validation of a single CNPJ (numeric or alphanumeric). No payment required.
| Name | Required | Description | Default |
|---|---|---|---|
| cnpj | Yes | Brazilian company tax ID (CNPJ), 14 digits, with or without punctuation. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states the validation is 'local' and 'free,' which discloses that no external API calls or payments are involved. However, it does not describe the return value format or behavior on invalid input, leaving gaps in understanding the tool's complete behavior. Since no annotations are provided, the description bears the full burden but only partially meets it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, front-loading the core action and modifiers ('Free local check-digit/format validation'). There is no redundancy or unnecessary detail, making it highly efficient for an AI agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter, no output schema), the description covers the purpose, scope, and cost. However, it omits the output type (e.g., boolean or error message), which is a notable gap for an agent deciding how to use the result. This reduces completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'cnpj' parameter (14 digits, with/without punctuation) at 100% coverage. The description adds value by clarifying that the tool accepts 'numeric or alphanumeric' CNPJ, which is additional information beyond the schema. This helps the agent understand the full range of valid inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool performs 'check-digit/format validation' of a CNPJ, specifying it is 'free' and works on a 'single' CNPJ. This distinguishes it clearly from sibling tools like lookup_company or validate_documents, which have different scopes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly mentions the tool is free and performs local validation, which guides the agent on when to use it (e.g., for quick, cost-free checks) and implies it should not be used for full company data retrieval. However, it does not explicitly name alternative tools or conditions to avoid.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate up to 100 Brazilian identifiers: CPF, CNPJ (incl. alphanumeric), PIS, license plates, Pix keys. Paid ($0.002).
| Name | Required | Description | Default |
|---|---|---|---|
| documents | Yes | Documents to validate (max 100). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description discloses cost ($0.002) and batch size (up to 100). It does not mention destructive actions, rate limits, authentication, or return format. Adequate but could be expanded.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with verb, scope, types, and cost. No extraneous words. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so description should explain return values. It does not. Also lacks prerequisites or error handling. However, parameter is well-defined. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter structure. The description adds the alphanumeric CNPJ detail and cost, which is helpful but not extensive. Score is baseline 3 as description adds marginal value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (validate), the resource (Brazilian identifiers), and lists specific types (CPF, CNPJ, PIS, license plates, Pix keys). It distinguishes from sibling 'validate_cnpj' by emphasizing batch and multiple types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions batch size and cost but does not explicitly guide when to use this tool versus single-type alternatives like validate_cnpj. Usage context is implied but not fully clarified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.2.2decode_boletodecode_nfe_keydecode_tender_idget_tenderget_tender_documentsget_tender_itemslookup_ceplookup_companylookup_company_fullresolve_tenderscreen_company_risksearch_companiessearch_tendersvalidate_cnpjvalidate_documentsEach tool serves a distinct function (decoding, tender info, company lookup, validation, CEP) with no overlaps. Tools are clearly separated by domain and action.
All tools follow the consistent snake_case verb_noun pattern (e.g., decode_boleto, get_tender, search_companies), using verbs like decode, lookup, get, search, validate.
15 tools are well-scoped for a specialized Brazilian public data server, covering tenders, companies, documents, CEP, and validation without being excessive.
The tool surface covers the core workflows: decoding common identifiers, full tender lifecycle (search, get, documents, items), company profiles with risk screening, and document validation, with no obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted MCP server for real-world data: business registries, sanctions, companies, domains, crypto.
CNPJ Brazil MCP — Brazilian company-registry (Receita Federal) lookup via
MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).
Brazilian legal stack in one MCP: lawsuits, court publications, case law, tenders, certificates.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thomenz/brdata-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server