INDIVIDUAL MCP TOOL

grade_repository

Score a public GitHub repository on how well an AI coding agent can work in it.

agentreadme.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://agentreadme.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for grade_repository and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

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

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentreadme
Remote MCP URL: https://agentreadme.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": {
    "agentreadme": {
      "url": "https://agentreadme.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

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

draft_agents_md — Draft an AGENTS.md for a public GitHub repository, built from what the repository actually contains: the install command implied by its lockfile, the commands it already declares, its real directory layout, and the specific problems found while grading it.
agent_readiness_findings — The published study behind the scoring: what the 864 most-starred software repositories on GitHub scored, which categories fail most often, and how the medians differ by language.