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.
Provides comprehensive development tools for FastMCP projects including documentation access, NPM package version management, and TypeScript type definitions retrieval. Enables developers to fetch FastMCP documentation, analyze NPM packages, and access MCP architecture information through natural language.
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.
Access a 24/7 AI senior developer with 26 specialized tools for the full software development lifecycle. Use tools like explain_code, debug_code, and refactor_code to analyze, debug, and optimize your codebase instantly. Deploy github_fix_issue and create_pr for seamless GitHub automation, or get ai_development_advice for architecture and career guidance.
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.
TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.
Connect to your TTRPG campaign's repository and database. Instead of retrieving prose, its 48 tools (20 read, 28 write) return typed state: 14 entity schemas (NPCs, factions, locations, sessions, lore), relationship and knowledge-graph queries, wiki blocks, and a narrative-state bundle of open threads and canon facts.