Developer Tools

looprepo.dev

Manages and evaluates agent-loop prompts for AI coding assistants.

1 endpoint22 known toolsFirst detected July 24, 2026Last detected July 24, 2026

ENDPOINT 1

https://mcp.looprepo.dev/mcp

No auth detected

MCP server metadata

Name: looprepo
Version: 1.1.0

Capabilities

tools

Server instructions

Search 168 vetted agent loops for Claude Code/Codex across 22 tools: discovery (search, trending, similar, for-your-stack, compare), deterministic A–F safety grading (loops_grade, loops_harden, harness_validate), Claude-use intake → loop recommendations (loops_intake_recommend), plain-language loop crafting (loops_craft), guides (articles_search), review-gated community submissions (loops_submit), and complete safe-loop harness bundles (loops_generate_harness). Start with loops_categories, loops_search, or loops_intake_recommend.

Known tools 22

loops_search

Search the looprepo directory of agent loops (/loop, /goal, /schedule, Ralph-style) for Claude Code and Codex.

loops_grade

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

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.

loops_compare

Compare 2–3 loops side by side: safety grade/score, type, risk, and boundedness signals.

loops_stats

Directory-wide stats: totals, category/type breakdown, safety-grade distribution, newest loops.

loops_of_the_week

The top loop of the trailing 7 days plus recent A/B-grade picks.

articles_search

Search looprepo's published guides/articles on loop engineering.

articles_get

Fetch one published guide: full markdown body plus metadata.

loops_submit

Submit a community loop to the review queue.

intake_prompt_get

Returns the read-only Claude-use intake prompt.

harness_validate

Deterministic checklist for a safe-loop harness: CLAUDE.md, PreToolUse/Stop hooks, evaluator, iteration budget, stop condition, deny-by-default.

loops_harden

Deterministic grade plus the exact edits to reach the next grade (exit condition, turn cap, verification, scope).

loops_grade_explain

Deterministic A–F grade plus an AI-written explanation and top-3 edits.

loops_craft

Describe a workflow in plain language and get one safe, copy-paste loop prompt with verification, stop conditions, and approval gates.

cme_tier_status

Your current tier (anonymous or CME Pro/Power), daily limits, and today's usage of crafted loops and harness builds.

beacon_run_report

Recent loop runs for your Mission Control beacon token: status, exit reason, turns, cost.