Measured Agents
Read-only MCP catalog of agent packs graded against human expert agreement
- Pricing
- Free
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 0.1.0
- Listing updated
- 2 days ago
About Measured Agents
Measured Agents is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
Measured Agents is a register of agent skills, plugins and MCP servers where each entry carries how closely it agrees with a human expert on held-out cases. The site is open about the starting point: no pack has yet been verified against a real expert, and a score only appears from 30 cards, with the 95 percent interval and sample size beside it. Below that a result is marked INDETERMINATE rather than shown as a number.
The MCP server exposes this register to an agent without a browser. It is read-only, with no key, account or tracking, and offers search_packs, list_packs, get_pack and list_professions. Entries can be filtered by status, profession (accountant, recruiter, privacy officer and others) or platform such as Claude Code, Cursor, ChatGPT, Apify or MCP.
Listing starts with a check of the vendor's public documentation and three EU AI Act questions. A free ten-card pilot follows, and a paid run of 30 or more cards, paid by the pack's publisher, repeats whenever the named model changes. The site says no price buys a score.
Install
Run in a terminal
claude mcp add --transport http catalog https://measuredagents.com/mcpAdd to Settings → Connectors → Add custom connector
https://measuredagents.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"catalog": {
"url": "https://measuredagents.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"catalog": {
"type": "http",
"url": "https://measuredagents.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"catalog": {
"serverUrl": "https://measuredagents.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"catalog": {
"type": "http",
"url": "https://measuredagents.com/mcp"
}
}
}Tools this server provides (4)
Taken from the project documentation; the running server may differ.
- list_packs
- Lists packs in the register.
- get_pack
- Returns one pack's entry.
- search_packs
- Searches packs by query.
- list_professions
- Lists the professions used to grade packs.
What it does
- Agreement scores
- Publishes how often a pack agrees with a human expert, with interval and sample size.
- Pack search
- Search the register by keyword, such as a profession.
- Status and profession filters
- Narrow entries by verification status, profession or platform.
- EU AI Act questions
- Each listing answers three questions on prohibited practices, disclosure and human oversight.
- Re-measurement
- Runs repeat when the model a pack was measured on changes.
- JSON catalog
- The same register is available as catalog.json.
Good for
- Compare agent skills for a profession before adopting one
- Check whether a pack's claims have been tested against an expert
- Let an agent look up vetted recruiting or SEO packs
- Review EU AI Act answers for a vendor's agent
Pricing
Free
Listing and pilot free; paid verification runs are paid by the pack publisher
Prices change. Check measuredagents.com before you buy.
Measured Agents FAQ
Does it need a key or account?
No. The server is read-only with no key, account or tracking.
Which tools does it have?
list_packs, get_pack, search_packs and list_professions.
Does a pack pay to get a better score?
The site says no price buys a score, and that it takes no commission on sales.
Is any pack verified yet?
The site says zero packs have been verified against a real expert so far.
Is Measured Agents free?
Yes. Measured Agents is free to use.
How do I add Measured Agents to Claude Code?
Run this command in your terminal: claude mcp add --transport http catalog https://measuredagents.com/mcp
What are the best alternatives to Measured Agents?
The closest alternatives to Measured Agents are Claude Code Ultimate Guide, BoardAgent, KitScout, signafAIde and Toolkien.
Alternatives to Measured Agents

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

BoardAgent
MCP serverRemote MCP server for a message board where only AI agents post, reply and vote
- 27 tools
- Remote
- Free
- Community directories

KitScout
MCP serverMCP search over about 84,000 MCP servers, Agent Skills and Claude Code plugins
- 4 tools
- Remote
- Free
- Developer tools

signafAIde
MCP serverLocal MCP server to set up, verify and check coverage of signed agent action records
Runs locally- 5 tools
- Freemium
- Security

Toolkien
MCP serverOne MCP gateway for all your MCP servers, with code mode, permissions and audit
Not checked yet- 3 tools
- Remote
- Open source
- AI models and LLM tooling
Lugh
MCP serverWrite, check and dry-run Lugh agent programs with policy, budgets and approvals
Runs locally- 5 tools
- Open source
- AI models and LLM tooling