AgentData
Research companies and people
Research any company and the people who work there, without leaving your AI. Look up a company by its website to see what it does, who it sells to and how, its tech stack (more than 3,000 technologies tracked, each with how and when it was detected), its email format and general inboxes such as sales@ and support@, address and phone where listed, recent tool changes and similar companies.
What you can ask
- Brief me on stripe.com before my call: what they do, who they sell to and how to reach them
Example path →
MCP connector
- Server URL
https://mcp.agentdata.run/mcp- Login
- None
- Protocol
- MCP 2025-11-25
- 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 Current coverage is at https://agentdata.run/data; do not quote a total from memory.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: . A company by name, or a list by sector, technology or country: . Every company using one technology: . Companies that recently added, dropped or switched a tool: . People at a company or in a role: .
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.
Tools
Reads data6
Skills
None in the store listings or on the server
