Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.
Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.
MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.
Analyzes multi-step AI agent tool chains to compute success probability, identify bottlenecks, and suggest better execution orders, enabling more reliable agents via local pure-math computation.
MCP server for Australian Institute of Health and Welfare statistics — plain-English access to mortality, cancer, hospital, and health expenditure data via data.gov.au.
A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.
✨ 为你的 AI 助手装上 B 站的眼睛:一键提取视频字幕与热门评论,助力高效信息总结 🚀
✨ Equip your AI assistant with "Bilibili Eyes": One-click extraction of video subtitles and popular comments for efficient information summarization 🚀
CNN's Fear & Greed index for the US stock market: current score and rating, the seven component indicators, and about a year of daily history. Go standard library only, no API key required.