Learning Resources

triedagents.com

Provides tools to search, list, and retrieve TriedAgents' rated AI-agent use cases, categories, and rating rubric details.

1 endpoint4 known toolsFirst detected October 21, 2026Last detected October 21, 2026

ENDPOINT 1

https://triedagents.com/mcp

No auth detected

MCP server metadata

Name: triedagents
Version: 1.0.0

Capabilities

tools

Server instructions

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.

Known tools 4

search_cases

Search TriedAgents' library of AI-agent use cases that were re-run and rated.

Inferred read-only

get_case

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.

Potential side effects

list_top_cases

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.

Inferred read-only

list_categories

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.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.triedagents]
url = "https://triedagents.com/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: triedagents
Remote MCP URL: https://triedagents.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "triedagents",
  "transport": "streamable-http",
  "url": "https://triedagents.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.