Agentrank Mcp

io.github.saviodamatoPublished by GitHub account saviodamatov0.1.3Updated Oct 24, 2026

Find real, verifiable businesses with provenance and source URLs - for AI agents.

The publisher's own server: Agentrank

VerifiedSTDIODesktop onlyWeb Search & ScrapingBusiness & Commerce

Overview

AI-generated overview

A local MCP server that lets an assistant search source-backed business listings and fetch company profiles with trust scores and provenance.

What you can do
Search businesses by natural-language intent, returning ranked results with fit and trust scores, risks and source URLs for each fact. Retrieve a full company profile by ID, including location, contact channels, hours, offers, policies and supporting evidence. Results are meant to be checked against their cited sources before being used.
When to use it
Useful when an assistant needs company or local business details (name, contacts, address, website) for Brazil, the US or Europe and should rely on cited sources rather than generated details.
Requirements
Runs locally as a Python package (agentrank-mcp) via uvx or from source. Requires an AgentRank API key in the AGENTRANK_API_KEY environment variable, obtained by registering an agent; AGENTRANK_BASE_URL is optional. Network access to the AgentRank API is needed.
Before you install
The API key is a credential sent as a bearer token; keep it out of shared configs. Free tier is limited to roughly 100 queries per day and 1500 per month per agent. Business data is sent to and returned from a third-party API, so verify provenance before acting on results.

Installation

In SourceWeft

  1. Open Agentrank Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AgentRank MCP server

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.

Use cases

  • 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.

Tools

  • 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.

1. Get an API key

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>.

2. Add it to your MCP client

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:

json
{  "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.)

Cursor

Add the same block under mcpServers in your Cursor MCP settings.

From source (no packaging)

bash
pip install -r requirements.txtAGENTRANK_API_KEY=ak_your_key_here python -m agentrank_mcp.server

And point your client's command at python with args ["-m", "agentrank_mcp.server"] and the folder on PYTHONPATH.

Environment variables

VarRequiredDefault
AGENTRANK_API_KEYyes—
AGENTRANK_BASE_URLnohttps://api.agentrank.intelligenceofcode.com

The key is never logged.

Beta & limits

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.

How agents should use the data

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

Source: README.md at commit c0582e8

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Agentrank integrations

Agentrank

info.agentrankOfficial publisher

Remote MCP server that lets an assistant check an AI agent's or x402 service's settlement-backed trust score and decide whether to pay or serve it.

Streamable HTTPWeb executable
FinanceNot indexed yetOct 24, 2026

AgentRank

Published by GitHub account superlowburn

AgentRank lets an assistant search, look up, evaluate and compare MCP servers, agent tools and AI skills using quality signals such as maintenance and adoption.

Streamable HTTPWeb executable
Knowledge & Memory5 toolsOct 25, 2026