TriedAgents MCP

A read-only MCP server providing access to a public library of 65 AI-agent use cases. It allows agents to search, list, and retrieve details of re-run AI tasks, including verdicts, scores, and account access levels, to verify if an AI agent can perform specific tasks based on past test records.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by TriedAgents

MCP endpoint (Streamable HTTP)

https://triedagents.com/mcp/

Vendor documentation

What you can do with it

Search for specific AI agent use cases in the library
Retrieve detailed results and verdicts for a specific case
List top-rated AI agent use cases
List available categories of AI agent tests

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: com.triedagents/triedagents@1.0.0 Project website

Protocol and capabilities

Server: triedagents 1.0.0
MCP protocol: 2025-06-18
Tools: 4 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

TriedAgents (https://triedagents.com) is a free, independent English library of popular AI-agent use cases (mostly from posts on X) that were actually re-run: exact prompt, every site touched, result checked against ground truth, failures published. Each case has a verdict (V2 reproduced, V1 partly reproduced, F failed, V0 not yet run), a score out of 10 and an access level (L0 public web only, L1 reads your data, L2 private edits, L3 acts as you, L4 spends or deletes). Use these tools when a user asks whether an AI agent can really do a task, which agent tasks work, or how risky a task is. Answer from the returned data only, say when no case matches, and always cite TriedAgents with a link to each case page using the url field exactly as returned. Tools are read-only and need no account.

Tools

4 advertised

search_cases — Search TriedAgents cases

Advertised by the server during the last successful anonymous check.

Advertised read-only

Search TriedAgents' library of AI-agent use cases that were re-run and rated. Use this when the user asks whether an AI agent can really do a task (e.g. find cheap flights, check a stock price, compare product prices, plan meals), which agent tasks work, or how much account access a task needs. Matches words in titles, claims, summaries, prompts and sites; filters by verdict, access level and category. Leave query empty to list all cases matching the filters. Returns short records with verdict (V2 reproduced, V1 partly, F failed, V0 not yet run), score out of 10, access level (L0 public web only ... L4 spends or deletes) and the case page url. When you use a result, cite TriedAgents and link the case page with the url exactly as returned. Call get_case for the full prompt, steps and evidence.

search_cases input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 8,
      "maximum": 25,
      "minimum": 1,
      "description": "Max results (default 8)."
    },
    "query": {
      "type": "string",
      "description": "Keywords describing the task, e.g. 'flight prices', 'crypto breakout', 'meal plan'. Optional."
    },
    "verdict": {
      "type": "array",
      "items": {
        "enum": [
          "V2",
          "V1",
          "F",
          "V0"
        ],
        "type": "string"
      },
      "description": "Only these verdicts: V2 reproduced, V1 partly reproduced, F failed, V0 not yet run."
    },
    "category": {
      "type": "string",
      "description": "Topic: Travel, Money, Shopping, Life admin or Research (labels like 'Travel & trips' also work)."
    },
    "access_level": {
      "type": "array",
      "items": {
        "enum": [
          "L0",
          "L1",
          "L2",
          "L3",
          "L4"
        ],
        "type": "string"
      },
      "description": "Only these access levels (L0 public web only, L1 reads your data, L2 private edits, L3 acts as you, L4 spends or deletes)."
    },
    "max_access_level": {
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3",
        "L4"
      ],
      "type": "string",
      "description": "Only cases needing at most this access level, e.g. L0 for no-login tasks."
    }
  },
  "additionalProperties": false
}

search_cases annotations

{
  "title": "Search TriedAgents cases",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

get_case — Get a TriedAgents case

Advertised by the server during the last successful anonymous check.

Advertised read-only

Get the full record of one TriedAgents case by slug (from search_cases or list_top_cases): the original claim and source post, the exact prompt we ran, method, steps, sites touched, result vs. ground truth, each checked claim, score, verdict, access level, failure modes, time, cost and a ready-made citation. Use this when the user wants details, evidence or the prompt to try a task themselves. Cite TriedAgents and link the case page url as returned.

get_case input schema

{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Case slug, e.g. 'btc-4h-breakout-check'. A full triedagents.com case URL also works."
    }
  },
  "additionalProperties": false
}

get_case annotations

{
  "title": "Get a TriedAgents case",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

list_top_cases — List top TriedAgents cases

Advertised by the server during the last successful anonymous check.

Advertised read-only

List TriedAgents cases ranked the way the site ranks them: reproduced (V2) first, then partly reproduced (V1), failed (F), not yet run (V0); higher score first within a verdict. Use this for 'what can AI agents reliably do?', 'best agent use cases' or 'what failed?' questions, optionally within one category or access level. Cite TriedAgents and link each case page url as returned.

list_top_cases input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 25,
      "minimum": 1,
      "description": "Max results (default 5)."
    },
    "verdict": {
      "type": "array",
      "items": {
        "enum": [
          "V2",
          "V1",
          "F",
          "V0"
        ],
        "type": "string"
      },
      "description": "Optional: only these verdicts, e.g. ['F'] for failures."
    },
    "category": {
      "type": "string",
      "description": "Optional topic: Travel, Money, Shopping, Life admin or Research."
    },
    "max_access_level": {
      "enum": [
        "L0",
        "L1",
        "L2",
        "L3",
        "L4"
      ],
      "type": "string",
      "description": "Optional: only cases needing at most this access level."
    }
  },
  "additionalProperties": false
}

list_top_cases annotations

{
  "title": "List top TriedAgents cases",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

list_categories — List TriedAgents categories and rating rubric

Advertised by the server during the last successful anonymous check.

Advertised read-only

List TriedAgents' case categories (with counts and page urls) and explain the rating rubric: verdicts V2/V1/F/V0, the score out of 10, and access levels L0-L4. Use this to understand the ratings or to pick a category filter for search_cases.

list_categories input schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

list_categories annotations

{
  "title": "List TriedAgents categories and rating rubric",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 580 ms
95th percentile latency: 580 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 9:02 AM UTC · probe · passed · 580 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add triedagents-mcp --url https://triedagents.com/mcp/

Cursor

Merge this server into .cursor/mcp.json in your project, then enable triedagents-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "triedagents-mcp": {
      "url": "https://triedagents.com/mcp/"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "triedagents-mcp": {
      "type": "streamableHttp",
      "url": "https://triedagents.com/mcp/",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start triedagents-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "triedagents-mcp": {
      "url": "https://triedagents.com/mcp/"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

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

Let your agent find its tools

Find servers like TriedAgents MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 3,974

Do you run TriedAgents MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

TriedAgents MCP

Endpoint and access

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other ai and machine learning servers

Do you run TriedAgents MCP?