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.
Enables AI agents and MCP clients to deterministically score creator short-video hooks for 3-second retention and scroll-stop effectiveness, returning structured JSON telemetry. It runs as a zero-dependency Python MCP server for seamless integration with Claude Desktop, Cursor, and Windsurf.
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.
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.
A read-only MCP server for Microsoft SQL Server that enables metadata discovery, parameterized queries, and query analysis with profile-based configuration and strict no-DML/DDL enforcement.
An AI-powered travel assistant connected to Claude via MCP that helps users plan Amazon Rainforest trips by providing directions, hotel recommendations, adventure spots, cultural sites, and travel precautions.
MCP server for Pi Network that enables AI agents to query Pi chain data (balances, transactions) and verify user tokens, with optional payment sending that is off by default.
Solana token risk-scoring MCP server for AI trading agents — 0-100 safety score, on-chain insider wallet cluster detection, mint/freeze authority checks, and historical risk data via 3 tools.
Enables Claude to interact with FTP servers through natural language commands, allowing users to list directories, download/upload files, create directories, and delete files/directories on FTP servers.
Hebbian learning MCP server with neural memory graphs, eligibility traces, and three-factor
reward signals. Associative memory that strengthens through use.