General Tools

agentdata.run

Provides general-purpose tools through the Model Context Protocol.

1 endpoint6 known toolsFirst detected May 29, 2026Last detected October 6, 2026

ENDPOINT 1

https://mcp.agentdata.run/mcp

No auth detected

MCP server metadata

Name: agentdata
Version: 2.2.0

Capabilities

tools.listChanged

Server instructions

AgentData: company data for AI agents, taken from companies' own websites: what a company does, the tools and technologies it runs, web signals, company contact details and people, as on the public website; with an AgentData account, also personal email addresses (with verification status). Current coverage is at https://agentdata.run/data; do not quote a total from memory. How to use it well: - One company by domain: lookup_company. A company by name, or a list by sector, technology or country: search_companies. Every company using one technology: get_technologies. Companies that recently added, dropped or switched a tool: get_signals. People at a company or in a role: find_people. - A domain that is not profiled yet is crawled on request; the reply says when to retry, usually within a few minutes, and nothing is charged. Some sites (adult, piracy, gambling) are never crawled; do not retry those. - Every response ends with a usage line. When an allowance runs out, wait for the reset it names rather than retrying in a loop. - A field we could not find is null, not guessed; say "not found" rather than inventing a value. - Describe an email address by its verification status (valid, catch-all, unknown); only call it verified when the status is valid.

Known tools 6

lookup_company

Use this when the user asks about one specific company and you know its website domain, for example to research an account before a call: what it does, sector and business model, headquarters where known, the tools and technologies it runs (each with how it was detected and when it was first and last seen), and web signals (pricing page, free trial, API docs, careers).

Inferred read-only

search_companies

Use this to find a company by name or part of its domain (query), or to build a list of companies by sector, business model, B2B or B2C, technology used or headquarters country.

Inferred read-only

find_people

Use this when the user wants people at a company or in a role: names, job titles, seniority, department and LinkedIn URLs found on company team, about and author pages.

Inferred read-only

get_technologies

Use this when the user asks which companies use a particular technology (for example Intercom, Zendesk, HubSpot, Shopify, Stripe), or which technologies are most used.

Inferred read-only

get_signals

Use this when the user asks which companies recently started, stopped or switched using a technology, for example companies that left Intercom or adopted HubSpot: set moved_from or moved_to.

Inferred read-only

check_usage

Use this before a large task to see how much of today's allowance is left: requests in the current 5-hour window, distinct companies today and, with an API key, contact reveals.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentdata]
url = "https://mcp.agentdata.run/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentdata": {
      "type": "http",
      "url": "https://mcp.agentdata.run/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentdata
Remote MCP URL: https://mcp.agentdata.run/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentdata": {
      "url": "https://mcp.agentdata.run/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentdata": {
      "type": "http",
      "url": "https://mcp.agentdata.run/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentdata",
  "transport": "streamable-http",
  "url": "https://mcp.agentdata.run/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentdata.run was fetched 2026-10-13T23:10:23.582Z.

Trust status Trusted

agentdata.run is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.