"A server or tool for local-only resources or information" matching MCP servers:

LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.

A custom MCP tool that integrates Perplexity AI's API with Claude Desktop, allowing Claude to perform web-based research and provide answers with citations.

An MCP server that retrieves relevant PDF chunks via local embeddings and returns them to IDE agents (Cursor, Kiro, Claude Code) for answer generation.

Enables read-only semantic search over a local document corpus with on-device embeddings and a local Chroma store, featuring symlink-hardened file access and structured error handling.

Enables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.

An MCP proxy that embeds tool definitions and returns only the top-k semantically relevant tools per query, reducing context usage and routing calls to upstream MCP servers.

A TypeScript MCP server that provides secure, read-only access to a locally hosted MySQL database for AI-agent workflows, with configurable policies and support for multiple MCP clients.

Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.

A local-first document retrieval MCP server that enables AI coding tools like Codex to search private local documents via semantic search and keyword boost, supporting ingestion of PDF, DOCX, TXT, Markdown, and HTML files.

MCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.

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.

A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.

Generates DeepWiki-style documentation for private code repositories with RAG-based Q\&A capabilities, semantic code search, and multi-language AST parsing. Supports local LLMs (Ollama) or cloud providers for privacy-focused codebase analysis.

A Model Context Protocol server that provides Claude with a dedicated space for structured thinking during complex problem-solving tasks, helping improve its reasoning capabilities.

A local MCP server that indexes codebases using Tree-sitter AST parsing and LanceDB, enabling AI models to search across repositories with sub-second latency.

Enables storing and retrieving text passages based on semantic meaning using local embeddings (Ollama) and vector storage (ChromaDB), allowing conversational memorization and retrieval of information.

A local-first MCP server for PageIndex — the vectorless, reasoning-based RAG framework. It lets local AI agents index and query local PDF and Markdown documents through a self-hosted PageIndex installation, without requiring any PageIndex cloud API key.

A proof of concept MCP server for Apache OFBiz

Provides fully local long-term memory for AI agents by enabling semantic search over notes and session logs using Ollama embeddings, with no external APIs or databases.

Enables AI assistants to perform semantic, hybrid, and filtered search on indexed local documentation with RAG capabilities.