The AgentRank MCP server allows AI agents to find and verify real-world businesses through two core tools:
search_businesses: Find businesses using natural-language queries (e.g., "pharmacy in Copacabana with phone", "software company in California"). Results are ranked and include:
fit_score — how well the business matches your intent
trust_score (0–100) — reliability/safety of the entity
Justification, risk notes, and source_url for each result
get_business_profile: Retrieve a full profile for a specific business using a company_id from search results, including location, contact channels (phone, email), business hours, offers, policies, and provenance-backed evidence with source URLs for every claim.
Key benefit: All data is backed by verifiable source URLs, preventing AI agents from hallucinating contact details like phone numbers or addresses.
It integrates with any MCP client (e.g., Claude Desktop, Cursor) via an API key.
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., "@AgentRank MCP find verified electricians in Chicago"
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.
MCP server for AI agents to search real, source-backed businesses. Every result carries a source URL and a trust score, so your agent acts on facts — never invented phone numbers or addresses. Coverage: Brazil, US, Europe (~2.7M businesses, growing).
Works with any MCP client (Claude Desktop, Cursor, …).
Public beta · free key, no invite · website: https://agentsafepath.com ·
official MCP registry: io.github.saviodamato/agentrank-mcp.
Business search / company lookup with source-backed data.
Local business search for agents (city + category + contact).
Company profile: contacts, address, website, provenance.
Source-backed company data instead of hallucinated details.
Related MCP server: Vexi MCP Server
search_businesses(intent, limit=10) — find businesses by a natural-language
intent (e.g. "farmácia em Copacabana com telefone", "software company in California").
Returns ranked results with fit_score, trust_score, justification, risks and the
source URL of each fact.
get_business_profile(company_id) — full profile of a result: location, contact
channels, hours, offers, policies and evidence, each with provenance and source.
Register your agent (free, no invite) at
https://agentsafepath.com/registrar.html — you receive a key once. It identifies
your agent and is sent as Authorization: Bearer <key>.
Edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:
{
"mcpServers": {
"agentrank": {
"command": "uvx",
"args": ["agentrank-mcp"],
"env": { "AGENTRANK_API_KEY": "ak_your_key_here" }
}
}
}Restart Claude Desktop. You'll see search_businesses and get_business_profile
available. (uvx comes with uv; or use the "From source"
option below.)
Add the same block under mcpServers in your Cursor MCP settings.
pip install -r requirements.txt
AGENTRANK_API_KEY=ak_your_key_here python -m agentrank_mcp.serverAnd point your client's command at python with args
["-m", "agentrank_mcp.server"] and the folder on PYTHONPATH.
Var | Required | Default |
| yes | — |
| no |
|
The key is never logged.
Public beta. Free tier: ~100 queries/day, 1500/month per agent (HTTP 429 with
Retry-After when exceeded). One key per agent; the key is shown once at registration.
Every result carries sources (source URLs). Verify provenance before acting —
data without a source should not be used. trust_score (0–100) reflects how safe the
entity is to commit to; fit_score reflects match to the intent.
mcp-name: io.github.saviodamato/agentrank-mcp
Retorna o perfil completo de uma empresa (por company_id de uma busca anterior).
Traz localização, canais de contato, horários, ofertas, políticas e evidências — cada afirmação com proveniência e source_url. Use para obter o telefone/endereço verificável de um resultado antes de agir sobre ele.
Args: company_id: o id retornado por search_businesses.
| Name | Required | Description | Default |
|---|---|---|---|
| company_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It details the data returned (localização, canais, horários, ofertas, políticas, evidências) and notes provenance with source_url. Implicitly read-only, but does not explicitly state side effects or permissions.
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?
Description is concise with bullet points and structured format. Includes an Args section but remains focused. Could be slightly tighter, but overall 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?
Given low schema coverage (0%) and no output schema or annotations, the description is quite complete. It lists major content areas and ties to sibling tool. Does not specify output format/JSON structure, but acceptable without output schema.
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?
Only one parameter, company_id, with schema coverage 0%. Description adds crucial context: 'o id retornado por search_businesses', clarifying its origin and usage beyond the schema's minimal type.
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 'Retorna o perfil completo de uma empresa' and specifies it retrieves location, contact channels, hours, etc. It distinguishes from sibling tool search_businesses by referencing company_id from a previous search.
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?
Explicitly advises 'Use para obter o telefone/endereço verificável de um resultado antes de agir sobre ele.' And mentions 'por company_id de uma busca anterior', indicating it should be used after search_businesses. No explicit alternatives but clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca empresas reais e verificáveis por uma intenção em linguagem natural.
Use quando o usuário quiser encontrar um negócio (ex.: "farmácia em Copacabana com telefone", "hotel em São Paulo", "software company in California"). Retorna empresas ranqueadas com fit_score, trust_score, justificativa, riscos e as FONTES (source_url) de cada dado — verifique a proveniência antes de agir. Nunca invente telefone, endereço ou e-mail: use apenas o que vier nas fontes.
Args: intent: a intenção em linguagem natural (ex.: "restaurante em Pinheiros"). limit: número máximo de resultados (1 a 50; padrão 10).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| intent | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry full weight. It adds important transparency about output features (fit_score, trust_score, risks, sources) and warns against inventing data, but does not explicitly state that the tool is read-only or non-destructive.
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?
Concise and well-structured with no unnecessary words. Purpose, usage, parameters, and warnings are all front-loaded in a few sentences.
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 simple input schema (2 parameters, no output schema), the description provides sufficient context: expected output (ranked businesses with scores, sources), usage examples, and a warning about data provenance.
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 description explains both parameters ('intent: a intenção em linguagem natural' and 'limit: número máximo de resultados') beyond the schema definitions, which only provide type and default values.
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 for real, verifiable businesses using natural language intent ('Busca empresas reais e verificáveis por uma intenção em linguagem natural'). It distinguishes from the sibling tool (get_business_profile) which is for retrieving individual business profiles.
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 clear usage context with examples ('Use quando o usuário quiser encontrar um negócio (ex.: farmácia em Copacabana...)') but does not explicitly exclude scenarios or mention alternatives beyond the sibling tool.
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.
v0.1.0get_business_profilesearch_businessesThe two tools have clearly distinct purposes: one searches for businesses, the other retrieves detailed profile of a specific business. There is no overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern (search_businesses, get_business_profile) using snake_case, making them predictable and easy to understand.
With only 2 tools, the set is minimal but appropriate for a read-only business lookup service. It covers the essential operations of searching and retrieving details without unnecessary bloat.
The tool set provides a complete workflow for finding and verifying business information: search to discover companies, then get profile to retrieve detailed data. No obvious gaps for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Owner-verified local business data for AI agents: profiles, hours, prices, with provenance.
Search and verify 360K+ business entities with trust scores and W3C credentials.
Live Google Maps business search, review, and photo data for AI agents over MCP.
Verified local business registry for AI agents. Currently serving Malaysia.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/saviodamato/agentrank-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
