AI Loop Library MCP server
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Version 2.1.0. A read-only, local MCP server for the
AI Loop Library and its 68 bounded work loops.
The calling agent uses its knowledge of the operator's project to choose a loop;
the server supplies searchable specs, runnable protocols, and design checks.
One Python file, Python 3.9+, standard library only at runtime. No write tools,
credentials, model calls, or hosted server to operate.
Install
Download the single file:
For Cursor or another stdio client:
The standalone repository
contains the same server. Run the following from its root, or from mcp/ in
the site repository:
Already installed? Download the file again or update your clone and reinstall,
then restart the MCP connection. Existing installations do not update themselves.
Tools
| Tool | Result |
| --- | --- |
| browse_catalog(category?) | Compact catalog digest for the calling agent to judge |
| search_loops(query, category?, limit?) | Ranked matches with why-matched explanations |
| get_loop(id_or_slug) | Full spec, canonical URL, verifier classification, loop kind |
| pick_loop_for_goal(goal, constraints?, limit?) | Lexical shortlist and confidence signal; the calling agent chooses |
| render_run_protocol(id_or_slug, goal?, risk_posture?, kind?, max_rounds?, max_minutes?) | Markdown protocol and copyable prompt sharing the same stop conditions and approval boundaries |
| critique_loop(loop_description) | Text-based lint, per-check findings, critical missing checks, and related loops |
| design_loop(goal, constraints?, cadence?, context?) | New loop scaffold with a suggested domain verifier and explicit TODOs |
| list_categories() | Category counts and library links |
| catalog_stats() | Counts, catalog source, update metadata, and cache status |
Session protocols honor round and minute caps. Scheduled-tick protocols use
experiment logs, per-tick/total spend guidance, and a two-tick no-progress stop.
max_rounds and max_minutes apply only to session protocols. Strict posture
requires explicit approval for shared-surface actions, including in copied prompts.
The linter recognizes explicit gate language and flags common negations such as
"without human approval" or "approval is optional". Critical missing verification,
stop, budget, or approval checks prevent a positive overall grade. Text matching
cannot establish safety or grant permission, regardless of the numeric score.
Resources: ailooplibrary://catalog and ailooplibrary://loop/{id}.
All tools declare readOnlyHint and idempotentHint.
Catalog loading and outages
Resolution order:
1. AI_LOOP_LIBRARY_CATALOG_PATH: an authoritative local JSON file, using either
the catalog.json or data/loops.json shape. An invalid explicit path fails.
2. AI_LOOP_LIBRARY_CATALOG_URL, defaulting to https://ailooplibrary.com/catalog.json.
3. Local fallback: catalog.json beside the server, then ../catalog.json, then
../data/loops.json.
The server caches a validated catalog in memory for five minutes. Remote fetches
have a ten-second timeout and a 4 MiB response limit. Validation and search indexing
finish before a new snapshot replaces the current one.