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., "@filed-mcp-server Search for Amazon business registrations in New York"
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 that gives AI agents access to US business entity data via the Filed.dev API. Search business registrations across 9 US states, SEC EDGAR filings, federal government contracts, and lobbying disclosures — all from any MCP-compatible client.
Sign up at filed.dev — free tier includes 100 lookups/month.
Claude Code:
claude mcp add filed -- npx -y filed-mcp-server
# Set your API key as an environment variable
export FILED_API_KEY=fd_live_your_key_hereOr add to your project's .mcp.json:
{
"mcpServers": {
"filed": {
"command": "npx",
"args": ["-y", "filed-mcp-server"],
"env": {
"FILED_API_KEY": "fd_live_your_key_here"
}
}
}
}Cursor:
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"filed": {
"command": "npx",
"args": ["-y", "filed-mcp-server"],
"env": {
"FILED_API_KEY": "fd_live_your_key_here"
}
}
}
}Claude Desktop:
Edit your config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"filed": {
"command": "npx",
"args": ["-y", "filed-mcp-server"],
"env": {
"FILED_API_KEY": "fd_live_your_key_here"
}
}
}
}Ask your AI: "Search for Lockheed Martin business registrations in Florida" or "Run a full company intelligence report on Palantir Technologies"
Related MCP server: edgar-mcp
Tool | Description |
| Search business entities by name in any of 9 US states (AK, CO, CT, DC, FL, IA, NY, OR, PA) |
| Get full entity details — officers, registered agent, filing history. Optionally enrich with federal data. |
| Search SEC EDGAR for company filings (10-K, 10-Q, 8-K, S-1, etc.) |
| Search federal government contracts from USASpending.gov |
| Search lobbying disclosures from the Senate LDA database |
| Power tool — searches all 9 states + SEC + contracts + lobbying for a company, returns unified intelligence report with cross-references |
"Search for Amazon business registrations in New York"
"Get the full details for entity FL:P06000113830 including federal data"
"Find SEC 10-K filings for Tesla"
"What federal contracts has Booz Allen Hamilton received?"
"Who lobbies for Pfizer and on what issues?"
"Run a comprehensive intelligence report on Anduril Industries"
Sample outputs from filed_company_intel for three defense companies:
Company | States | Entities | Contracts | Lobbying | Output |
Lockheed Martin | 8/9 | 62 | $4.96B | $925K | |
Anduril Industries | 6/9 | 14 | $560M | $1.02M | |
Palantir Technologies | 3/9 | 13 | $350M | $2.1M |
See demo/prompts.md for orchestration prompts that pair this server with Notion MCP to build a structured intelligence workspace.
This server works well alongside Notion MCP for building persistent, structured intelligence workspaces. Configure both servers:
{
"mcpServers": {
"filed": {
"command": "npx",
"args": ["-y", "filed-mcp-server"],
"env": {
"FILED_API_KEY": "your_key_here"
}
},
"notion": {
"command": "npx",
"args": ["-y", "@notionhq/notion-mcp-server"],
"env": {
"OPENAPI_MCP_HEADERS": "{\"Authorization\": \"Bearer ntn_your_token\", \"Notion-Version\": \"2022-06-28\"}"
}
}
}
}Then ask: "Research Palantir Technologies using Filed and add the findings to my Notion intelligence hub."
git clone https://github.com/mgrantley/filed-mcp-server.git
cd filed-mcp-server
npm install
npm run build
FILED_API_KEY=your_key node dist/index.jsState registries: AK, CO, CT, DC, FL, IA, NY, OR, PA
Federal sources:
SEC EDGAR — company filings (10-K, 10-Q, 8-K, S-1, proxy statements, etc.)
USASpending.gov — federal government contracts and awards
Senate LDA — lobbying disclosures (clients, registrants, amounts, issue areas)
More states and sources are added regularly. See filed.dev/docs for current coverage.
MIT
Run comprehensive intelligence gathering on a company. Searches across all 9 US states (AK, CO, CT, DC, FL, IA, NY, OR, PA) for business registrations, then checks SEC filings, federal contracts, and lobbying disclosures. Returns a unified intelligence report with cross-reference findings. NOTE: This tool makes multiple API calls (up to ~15) and uses more credits than individual tools.
| Name | Required | Description | Default |
|---|---|---|---|
| company_name | Yes | Company name to investigate | |
| states | No | Specific states to search (default: all 9). Use 2-letter codes. | |
| include_sec | No | Search SEC EDGAR filings (default: true) | |
| include_contracts | No | Search federal contracts (default: true) | |
| include_lobbying | No | Search lobbying disclosures (default: true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the tool makes multiple API calls (up to ~15) and uses more credits, providing behavioral transparency. No annotations are present, so description carries full weight. However, it does not detail response structure or error behaviors.
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 plus a note, front-loaded with the core purpose, then detailing scope and behavioral note. Every sentence adds value with no 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 5 parameters and no output schema, the description covers the tool's function well but lacks specifics on output format. The mention of 'unified intelligence report' is helpful but vague. Overall 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 the description does not add significant meaning beyond schema definitions. The description loosely references the parameters but offers no additional context on formats or defaults beyond what schema already provides.
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 runs comprehensive intelligence gathering on a company, searching across 9 US states for business registrations, SEC filings, federal contracts, and lobbying disclosures, and returns a unified report. This distinguishes it from sibling tools that focus on individual searches.
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 comprehensive company intel and notes higher credit cost, but does not explicitly specify when to use vs. alternatives or exclude scenarios. Sibling tool list provides context but no direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full details for a specific business entity including officers, registered agent, filing history, and current status. Optionally enrich with federal data (SEC filings, government contracts, lobbying disclosures). The entity ID format is 'STATE:ID' (e.g., 'FL:P06000113830').
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Entity ID from search results (format: STATE:ID, e.g., 'FL:P06000113830') | |
| include_federal | No | Include SEC filings, federal contracts, and lobbying data (default: false). Uses additional API credits. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description must compensate. It discloses that include_federal uses additional API credits but omits authentication requirements, rate limits, or data freshness. Behavioral traits beyond parameter cost are not described.
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 efficiently convey purpose, scope, and key constraint (ID format). No redundant or 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?
Covers main content, ID format, and optional parameter cost. Lacks explanation of response structure or any usage restrictions (e.g., need for API key). Still sufficient for a simple retrieval tool with two parameters.
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 covers both parameters completely. Description adds value by specifying the ID format with an example and noting that include_federal incurs extra cost, which is not in 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?
Description clearly states 'Get full details for a specific business entity' and enumerates included content (officers, agent, filing history, status). It also notes optional federal data enrichment, distinguishing it from search siblings.
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?
Provides important context on entity ID format and optional parameter cost, but no explicit guidance on when to use this tool versus siblings like filed_company_intel or the search tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search federal government contracts from USASpending.gov. Find which companies receive government contracts, from which agencies, and for how much.
| Name | Required | Description | Default |
|---|---|---|---|
| recipient | No | Contractor/recipient name to search | |
| agency | No | Awarding agency name | |
| min_amount | No | Minimum award amount in dollars | |
| max_amount | No | Maximum award amount in dollars | |
| naics | No | NAICS industry code | |
| start_date | No | Contracts starting after this date (YYYY-MM-DD) | |
| end_date | No | Contracts starting before this date (YYYY-MM-DD) | |
| sort | No | Sort field (e.g., 'Award Amount', 'Start Date') | |
| limit | No | Max results, up to 100 (default: 25) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden; it lacks behavioral traits like read-only, auth needs, 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?
Two efficient sentences: purpose and outcome. No fluff.
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?
Adequate for a search tool, but missing guidance on how parameters combine (AND/OR), default behavior, or beyond-limit handling.
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 100% with descriptions; description adds no additional meaning beyond summarizing the 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?
Clear verb+resource+source: 'Search federal government contracts from USASpending.gov.' Distinct from siblings like filed_search_lobbying and filed_search_sec.
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 for searching contracts, but no explicit when-to-use or alternatives compared to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search US business entities by name across 9 states (AK, CO, CT, DC, FL, IA, NY, OR, PA). Returns matching companies with state registration details including entity type, status, and formation date.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Business name to search (required if agent not provided) | |
| state | Yes | Two-letter state code (AK, CO, CT, DC, FL, IA, NY, OR, PA) | |
| agent | No | Registered agent name to search | |
| status | No | Filter by status | |
| type | No | Filter by entity type | |
| limit | No | Results per page, max 50 (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It states the tool returns matching companies with registration details, which provides basic output transparency, but it does not mention pagination, rate limits, or the read-only nature of the operation.
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 immediately states the core purpose, lists supported states, and summarizes return fields. Every word is essential, with no redundancy or wasted space.
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?
The description includes return details (entity type, status, formation date), which is helpful since no output schema is provided. However, it omits mention of pagination controls or the limit parameter, which are defined in the schema but not referenced in the description.
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 has 100% description coverage, so the baseline is 3. The description adds context that the search is by name across states, which aligns with the name and state parameters, but does not provide additional semantic value beyond the schema's parameter descriptions.
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 US business entities by name across 9 specified states, which distinctly differentiates it from sibling tools like filed_search_contracts or filed_search_sec that search different domains.
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 (searching for business entities by name or registered agent) and lists the supported states, but does not explicitly state when not to use or compare to alternatives, leaving some ambiguity despite clear sibling distinctions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search federal lobbying disclosures from the Senate LDA database. Find which companies hire lobbyists, what issues they lobby on, and how much they spend.
| Name | Required | Description | Default |
|---|---|---|---|
| client_name | No | Client company being represented | |
| registrant_name | No | Lobbying firm name | |
| issue_code | No | Issue area code: HCR (Health), DEF (Defense), TAX (Taxation), ENV (Environment), TRD (Trade), etc. | |
| filing_year | No | Filing year (e.g., '2025') | |
| filing_type | No | Filing type: RR (Registration), Q1, Q2, Q3, Q4 (Quarterly) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry full behavioral transparency. It does not mention read/write nature, auth requirements, rate limits, or any limitations, leaving the agent unaware of important behavioral traits.
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, front-loaded with the main action, and contains no redundant information. Every sentence 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?
For a search tool with 5 optional parameters and no output schema, the description covers the core functionality and output types (companies, issues, spending). It could mention that it returns filings or records, but overall it is reasonably complete.
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 descriptions. The tool description adds context about what can be found (companies, issues, spending) but does not significantly enhance 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 the tool searches federal lobbying disclosures from the Senate LDA database, with specific examples of what can be found (companies, issues, spending). This distinguishes it from sibling tools like filed_search_contracts or filed_search_sec.
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 explains the tool's purpose but does not explicitly state when to use it versus alternatives or provide exclusions. The context is implied through sibling names, but no direct guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search SEC EDGAR filings by company name, CIK number, form type, or industry code. Find 10-K annual reports, 10-Q quarterlies, 8-K event disclosures, S-1 registrations, and more.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Company name or keyword to search | |
| forms | No | Comma-separated form types to filter: 10-K, 10-Q, 8-K, S-1, DEF 14A, 13F-HR, etc. | |
| cik | No | SEC Central Index Key | |
| sic | No | Standard Industrial Classification code | |
| start_date | No | Filter filings after this date (YYYY-MM-DD) | |
| end_date | No | Filter filings before this date (YYYY-MM-DD) | |
| limit | No | Max results, up to 100 (default: 25) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as rate limits, pagination, or whether results include full text or metadata. The description only states the tool searches and finds filings, leaving key behavioral aspects unclear.
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 with no fluff, front-loading the purpose. Every word 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?
Given 7 parameters, no required fields, and no output schema, the description adequately states the search capability but lacks details on return format, pagination (limit up to 100), and edge cases. It is minimally sufficient 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%, so the schema already details all parameters. The description adds marginal value by mentioning example form types, but does not elaborate on parameter usage or constraints beyond what the schema provides. 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 searches SEC EDGAR filings with specific criteria (company name, CIK, form type, industry code) and lists example forms. However, it does not differentiate from sibling tools like filed_search_contracts or filed_search_lobbying, which target specific filing subsets.
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 general SEC filing search usage but provides no explicit guidance on when to use this tool versus alternatives. It does not specify exclusions or prerequisites, relying on context from the tool name and sibling list.
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.
v1.0.0filed_company_intelfiled_get_entityfiled_search_contractsfiled_search_entitiesfiled_search_lobbyingfiled_search_secEach tool targets a distinct data source or operation (composite intelligence, entity details, contracts, entities, lobbying, SEC filings). There is no overlap in purpose; even the composite tool is clearly a higher-level wrapper.
All tools follow the consistent pattern 'filed_<verb>_<noun>' (e.g., filed_search_entities, filed_get_entity). The only deviation is 'filed_company_intel', where 'intel' is a noun, but it still fits the pattern and is clear.
Six tools is appropriate for the domain of business intelligence research. The set covers search, retrieval, and a composite report tool without being overwhelming or too sparse.
The tool surface covers the full research workflow: finding companies (search_entities), getting detailed information (get_entity), and checking federal records (contracts, lobbying, SEC). The company_intel tool ties it all together. No obvious gaps for its read-only intelligence purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
Hosted MCP server for live public-data APIs and Skills for AI agents.
Hosted MCP server for real-world data: business registries, sanctions, companies, domains, crypto.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mgrantley/filed-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
