Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.
MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.
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.
Bridge that lets stdio-only MCP clients connect to remote MCP servers with OAuth and other auth support, enabling local clients to use remote, authorized MCP servers.
Enables claude.ai on your phone to act as a peer in the agentsync coordination mesh, using GitHub contents API instead of git to read and update claims.json. Provides tools for surveying, claiming, conflict-checking, updating status, releasing, history, and mailbox notes.
Enables AI assistants to perform web and image searches through a Google Programmable Search Engine, with pagination, language/country filters, and safe search.
Enables AI agents and their users to retrieve scored news sentiment, narratives, historical readings, and cited sources for Bitcoin, gold, and oil, with tamper-evident, time-stamped data for trading decisions.
Enables AI coding assistants to validate HTML/CSS markup using W3C APIs, perform technical SEO audits, check broken links, and validate JSON-LD schemas directly in local workspaces.