"smart" matching MCP servers:

An MCP server for Claude Code that enables semantic search of past session transcripts and intelligent session forking, allowing users to find and resume from relevant previous conversations with full context.

A local-first MCP server that enables semantic search over PDF and DOCX documents using structure-aware parsing and vector storage. It allows users to query their local knowledge base through Claude Code without cloud dependencies or GPU requirements.

Generates complex draw.io diagrams (tables, kanbans, GANTT) using a local 9B LLM with RAG, featuring a real-time dashboard and CI/CD pipeline.

A single MCP server that fronts many downstream MCP servers and Skills, exposing only four tools (search, call_tool, use_skill, admin) so that an agent's context window only ever sees search results on demand.

A smart MCP server for multi-engine web search with AI-powered results, supporting 6 search engines and web content extraction.

Connects AI assistants to SmartGym on Mac, enabling users to review workouts, tweak routines, and build training programs in plain English, with changes syncing to iPhone and Apple Watch.

Context-aware web fetching for LLMs, providing 7 tools to check page size, fetch with truncation, extract code/sections/links/tables, and paginate large documents.

Enables MCP-capable agents to profile datasets and render CSV/TSV/TXT/JSON data into standalone interactive ECharts HTML charts fully offline, returning the HTML artifact plus rendering statistics in the same response.

AI-powered video clipping server that analyzes subtitles and audio to detect highlight moments, then generates platform-adapted short clips from long videos.

Quality gate for AI video renders: checks keyframes and clips for blur, flicker, frozen or black frames and look drift, and decides PASS / RETRY / SWITCH_TO_FALLBACK / HALT with a spend ledger.

A stateful MCP server that provides persistent memory, deterministic static analysis, and evolving conventions for AI coding assistants.

A lightweight MCP server that enables AI assistants to interact with the local machine through terminal, filesystem, and Python execution tools.

Enables turning Gmail messages and natural-language requests into reviewed, workload-aware Things 3 tasks, with read-only Gmail access and explicit approval before anything is created.

Enables users to ask plain-English questions against MySQL, PostgreSQL, SQLite, SQL Server, Oracle, and MariaDB databases by auto-detecting schemas and converting requests into safe, read-only SQL queries.

Enables AI agents to safely work on Windows developer workstations through governed, project-scoped filesystem access, durable command execution, bounded search, Windows operations, and resource-aware runtime controls. It also supports optional developer-context backends for code navigation, repository graph exploration, and memory retrieval.

Provides AI assistants with real-time and historical Chinese stock, ETF, index, and futures data via Tushare Pro API, enabling natural language queries for financial analysis and market monitoring.

Federating gateway for AI agents to discover and call tools from multiple MCP servers with intelligent search and dynamic tool registration.

Enables natural language querying of any SQL database by converting plain English questions into SQL queries, with auto-schema detection and safety features.

MCP server for searching and reading arXiv papers from AI assistants, with built-in rate limiting to avoid API blocks.

MCP server that triages GitHub issues by classifying, ranking priority, and assigning an engineer using a local LLM (Ollama) with full traceability.