# AgentData (remote · mcp.agentdata.run)

Free company data for AI agents: profiles, tech stacks, contact details and people. No sign-in.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-28

## Components

- remote · `mcp.agentdata.run`: 69/100 (this document), [markdown](https://verifymcp.io/servers/run-agentdata-agentdata/mcp.md), [page](https://verifymcp.io/servers/run-agentdata-agentdata/mcp)

## Channel facts

- Endpoint: `https://mcp.agentdata.run/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-28.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1719 tokens (~286/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the AgentData MCP server?

AgentData is a hosted endpoint at https://mcp.agentdata.run/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http run-agentdata-agentdata 'https://mcp.agentdata.run/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.run-agentdata-agentdata]
url = "https://mcp.agentdata.run/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "run-agentdata-agentdata": {
      "type": "remote",
      "url": "https://mcp.agentdata.run/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add run-agentdata-agentdata --url 'https://mcp.agentdata.run/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  run-agentdata-agentdata:
    url: "https://mcp.agentdata.run/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "run-agentdata-agentdata": {
      "Transport": "http",
      "Url": "https://mcp.agentdata.run/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add run-agentdata-agentdata -t streamable-http -u 'https://mcp.agentdata.run/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-28 (score 69)

First indexed and scored.

## MCP tools (6)

### `lookup_company` (~283 tokens)

Look up a 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). Without an API key it returns everything the public company page shows to a visitor who is not signed in: company facts (employees, funding stage, founded, headquarters, sales motion, tech sophistication), the email format (for example {first}.{last}@domain), general inboxes such as info@ and sales@, address and phone where listed, how many email addresses and people were found, the top people's titles, seniority and LinkedIn URLs (not names), recent activity, recent tool changes and similar companies. Personal email addresses and names need an API key; for names at a company use find_people with its domain. A domain not profiled yet is crawled on request: the reply says when to retry, usually within a few minutes, and nothing is charged. Do not use it to find a company by name; use search_companies to get the domain first.

Input parameters:

- `domain` (string, required): Bare domain, e.g. stripe.com (no https://, no path)

### `search_companies` (~335 tokens)

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. Returns up to 20 company summaries per page, with how many email addresses were found for each. Use lookup_company for one company's full record, and get_technologies to page through every company using one tool. Works without an API key; no contact reveals.

Input parameters:

- `b2b` (string): b2b, b2c or both
- `country` (string): Headquarters country, ISO-2 code such as US or GB
- `model` (string): Business model
- `page` (integer): Page number, 20 companies per page
- `query` (string): Company name or domain fragment, e.g. 'notion' or 'stripe.com'. Used on its own; filters below are ignored when set.
- `sector` (string): Industry sector, exact label from the list
- `size` (string): Estimate, not headcount: a band by how many people and addresses we found on the company's own website: micro (1-5), small (6-20), medium (21-60), large (61+). Large companies often publish few, so d…
- `tech` (string): Technology name as detected, e.g. 'Intercom', 'HubSpot', 'Shopify'
- `vertical` (string): Vertical inside the sector, free text as stored, e.g. 'B2B SaaS'

### `find_people` (~278 tokens)

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. Filter by company domain, name, title, seniority, department, sector or B2B/B2C. Without an API key it returns what the public people directory shows to a visitor who is not signed in: the first 20 matches, with the last 5 withheld, and no email addresses. Narrow the filters (for example a domain plus a title) to get the right people into that first page.

Input parameters:

- `b2b_b2c` (string): b2b, b2c or both
- `department` (string)
- `domain` (string): Only people at this company domain, e.g. stripe.com
- `has_email` (boolean): Only people with an email address found (the address itself needs an API key)
- `has_linkedin` (boolean): Only people with a LinkedIn URL
- `q` (string): Name search
- `sector` (string): Industry sector, exact label from the list
- `seniority` (string): founder, executive, senior, mid or junior
- `title` (string): Title contains, e.g. 'CTO', 'Head of Sales'

### `get_technologies` (~203 tokens)

Technologies and who uses them

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. With a slug: companies detected using that technology, 20 per page. company_count is every company detected using it; listed_count is how many the list can page through, so stop at page ceil(listed_count / 20). Without a slug: the technology index, most-used first, with company counts (default 100, up to 1,000). Slugs are lower-case with hyphens, e.g. intercom, hubspot, google-analytics, shopify. Works without an API key; no contact reveals.

Input parameters:

- `limit` (integer): Index size when no slug is given, default 100
- `page` (integer): Page of companies when a slug is given
- `slug` (string): Technology slug, e.g. intercom

### `get_signals` (~284 tokens)

Switch 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. Also covers growth and hiring changes. Newest first. Changes are recorded as each site is re-crawled, so an empty result means none recorded yet, not that none happened. Works without an API key; no contact reveals.

Input parameters:

- `b2b_b2c` (string): b2b, b2c or both
- `days` (integer): Only signals detected in the last N days
- `limit` (integer): Results per page, default 20
- `moved_from` (string): Technology the company dropped, e.g. 'Zendesk'
- `moved_to` (string): Technology the company adopted, e.g. 'HubSpot'
- `offset` (integer)
- `sector` (string): Industry sector, exact label from the list
- `size` (string): Estimate, not headcount: a band by how many people and addresses we found on the company's own website: micro (1-5), small (6-20), medium (21-60), large (61+). Large companies often publish few, so d…
- `type` (string): Signal type; omit for all technology signals

### `check_usage` (~51 tokens)

Plan and 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. Free and not counted.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/run-agentdata-agentdata/mcp#diagnostics

## Score history

- 2026-09-28: 69

## Common questions

### What is the AgentData MCP server?

AgentData is an MCP server listed in the public MCP registry as run.agentdata/agentdata. Free company data for AI agents: profiles, tech stacks, contact details and people. No sign-in. This page covers its hosted endpoint (https://mcp.agentdata.run/mcp).

### Is the AgentData MCP server safe to use?

AgentData scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AgentData MCP server expose?

AgentData exposes 6 tools: lookup_company, search_companies, find_people, get_technologies, get_signals, check_usage. Their descriptions and schemas cost roughly 1,434 tokens of context every time the server is loaded.

### Does the AgentData MCP server require authentication?

No. We connected to AgentData without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentData MCP server still maintained?

AgentData is still listed as active in the MCP registry. We last reached this channel on 28 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.agentdata.run/mcp
- Repository: https://github.com/nick-timms/agentdata-mcp-server
- Website: https://agentdata.run/docs/mcp
- Changelog RSS feed: https://verifymcp.io/servers/run-agentdata-agentdata/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/run-agentdata-agentdata/mcp.json
- HTML version of this page: https://verifymcp.io/servers/run-agentdata-agentdata/mcp