17442 Model Context Protocol servers — searchable, rated, ready to install.
Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。
Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery.
Transactional refactoring MCP with 11 evidence-backed tools, hash-bound previews, and rollback.
Extract regular expressions from code, each with a ReDoS safety verdict.
Icons for agentic development: search & fetch 366,000+ open-source icons as SVG/PNG. No API key.
Audit, reschedule and author Microsoft Project schedules. No Java, no Project install.
Unofficial MCP server for reading and managing Cloudcraft architecture blueprints
Read-only access to secrets in a local KeePassXC vault. Runs commands with them injected.
Honest claim corroboration for AI agents: syndication-aware independent-source counting.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Search for books and book-related products, with access to product and delivery details
Know when the sun can make vitamin D where you are, for your skin type. Live UV data.
US state DMV data: vehicle and EV registrations, office locators, live wait times
Read-only source search and retrieval across configured GitHub repositories
Local, read-only structural code navigation and bounded dependency analysis for source repositories.
Bounded tools for rendering, extraction, RAG, enrichment, local discovery and review analysis.
Stops agents double-firing side effects: 1,000 racing duplicates, exactly one execution.
Real, live npm/PyPI docs and OSV.dev vulnerability data for AI coding agents. No fake data.
Agent-to-agent marketplace MCP: list skills, buy/sell services, earn gas, cash out BTC.
Local agent spend-policy checks. No funds, keys, payment authority, or network access.
Read-only access to your tabletop campaigns: codex, sessions, and session notes.
Reproducible benchmarks and reliability evidence for agent tools.
POST /mcp