← looprepo.dev

INDIVIDUAL MCP TOOL

loops_grade

Grade any agent-loop prompt A–F with the same deterministic, default-fail Safety Score that gates the looprepo directory.

looprepo.devnone authenticationAvailability not checked

Input schema

{}

Risk classification

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.

Parent endpoint

looprepo.dev

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.looprepo]
url = "https://mcp.looprepo.dev/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "looprepo": {
      "type": "http",
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: looprepo
Remote MCP URL: https://mcp.looprepo.dev/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": {
    "looprepo": {
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "looprepo": {
      "type": "http",
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "looprepo",
  "transport": "streamable-http",
  "url": "https://mcp.looprepo.dev/mcp"
}
MCP Inspector

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

Related tools

  • loops_search — Search the looprepo directory of agent loops (/loop, /goal, /schedule, Ralph-style) for Claude Code and Codex.
  • loops_get — Get one loop by slug: full prompt, usage notes (when to use / how it works / safety), attribution, and stats.
  • loops_categories — List all categories and loop types with published-loop counts.
  • loops_intake_recommend — Given a read-only intake report pasted from Claude, Claude Code, Cowork, Codex, or another agent, infer the goal/workflows and return ranked real looprepo loops plus a harness-ready builder prefill.
  • loops_generate_harness — Generate a complete safe-loop harness bundle (CLAUDE.md, .claude/settings.json PreToolUse+Stop hooks, slash commands, fresh-context default-fail evaluator agent, prd.json, progress/handoff templates).
  • loops_trending — Top loops by upvotes + copies over a recent window.
  • loops_similar — Loops related to a given slug — same category, matching intent, and text similarity.
  • loops_for_stack — Describe your tools/stack (e.g.