Skip to content
MCP server

TriedAgents

Look up AI agent use cases that were re-run, scored out of 10 and graded by access level

Install
Pricing
Free
Platforms
Web, API
Runs
Remotely
Version
1.0.0
Listing updated
1 day ago

About TriedAgents

TriedAgents 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.

TriedAgents takes claims about what AI agents can do, mostly from posts on X, and re-runs each with the exact prompt. Results are checked against ground truth and published with a verdict, a score out of 10 and an access level from L0 (public web only) to L4. Failures are included.

At the time of the page, the site reports 67 cases run: 30 reproduced, 32 partly reproduced and 5 failed, with two awaiting testing. Entries are specific, such as whether a founder built a site with a coding agent in about two hours or whether a prescription drug seller's prices match a pharmacy chain, and each shows the date and how long the agent took.

The MCP server makes those verdicts, scores, access levels and links queryable from ChatGPT, Claude or Cursor, so an assistant can check whether an agent claim holds up before you grant it access to accounts. A daily email with one re-run case is optional.

Install

Run in a terminal

claude mcp add --transport http triedagents https://triedagents.com/mcp/

Add to Settings → Connectors → Add custom connector

https://triedagents.com/mcp/
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "triedagents": {
      "url": "https://triedagents.com/mcp/"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "triedagents": {
      "type": "http",
      "url": "https://triedagents.com/mcp/"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "triedagents": {
      "serverUrl": "https://triedagents.com/mcp/"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "triedagents": {
      "type": "http",
      "url": "https://triedagents.com/mcp/"
    }
  }
}

What it does

Verdicts
Each case is Reproduced, Partly reproduced or Failed.
Scores out of 10
Rates how well the claim held up.
Access levels
Grades the access an agent needed from L0 to L4.
Failures published
Cases that did not reproduce are listed too.
Source links
Entries link back to the evidence.

Good for

  • Check an AI agent claim before relying on it
  • Find cases that needed only public web access
  • Compare how often agent claims fully reproduced
  • Pull a verified example for an article

Pricing

Free

Free

Prices change. Check triedagents.com before you buy.

TriedAgents FAQ

What do access levels mean?

They run from L0 (public web only) to L4; the site has a page explaining scoring.

Are failures shown?

Yes, the site states failures are published.

Where do cases come from?

Mostly claims from posts on X.

Is it free?

The site and the daily email are free.

Is TriedAgents free?

Yes. TriedAgents is free to use.

How do I add TriedAgents to Claude Code?

Run this command in your terminal: claude mcp add --transport http triedagents https://triedagents.com/mcp/

What are the best alternatives to TriedAgents?

The closest alternatives to TriedAgents are Claude Code Ultimate Guide, signafAIde, OpenNash Podcasts, Toolkien and Lugh.

Alternatives to TriedAgents

  1. MCP 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
  2. signafAIde

    MCP server

    Local MCP server to set up, verify and check coverage of signed agent action records

    Runs locally
    • 5 tools
    • Freemium
    • Security
  3. Search business and tech podcast transcripts and sourced quotes over MCP, no key needed

    • 10 tools
    • Remote
    • Free
    • News and media
  4. Toolkien

    MCP server

    One 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
  5. Lugh

    MCP server

    Write, check and dry-run Lugh agent programs with policy, budgets and approvals

    Runs locally
    • 5 tools
    • Open source
    • AI models and LLM tooling
  6. HypePaper

    MCP server

    Research papers, benchmarks, citations and topic experts for AI assistants

    • 58 tools
    • Remote
    • Freemium
    • AI models and LLM tooling