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 "Deploy 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.
Inputs: company_id (required).
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).
Inputs: intent (required), limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The 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.
Owner-verified local business data for AI agents: profiles, hours, prices, with provenance.
Company profile lookup and B2B company search for AI agents.
Search B2B people, companies and local businesses and build lead lists from your AI assistant.
Search and verify 360K+ business entities with trust scores and W3C credentials.
