"A tool for searching local files" matching MCP servers:

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.

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.

A local-first MCP server for indexing and searching codebases using PostgreSQL and Ollama embeddings, ensuring complete privacy and zero API costs.

A local MCP server for RGPD-compliant document Q&A, enabling Claude Code to ingest, query, search, delete, and audit personal documents entirely on-device.

A local-first RAG system that indexes personal documents and enables querying them via an MCP tool, keeping data private with local embeddings.

Provides tools for searching and reading local files, supporting metadata filters, PDF full-text keyword search, and sandboxed file access.

A local knowledge base MCP server that enables retrieval and evidence-based Q&A over Obsidian Markdown notes, with high-recall embedding search, chunked indexing, hybrid retrieval, and three STDIO MCP tools for agent-driven recollection and quality-gated recall.

MCP server enabling Claude Desktop to answer questions from local Word and PDF documents by searching a vector index built from their contents.

Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet gets access to solutions that Opus spent 20 tool calls discovering. Search is free with feedback, and contributing earns credits.

Persistent local semantic memory for MCP tools, enabling storing and searching notes by meaning using local embeddings and SQLite.

An MCP server for indexing and searching local text files using late-interaction retrieval (ColBERT-style MaxSim), enabling token-level relevance matching.

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.

An MCP server that enables searching Merill's Weekly Microsoft AI Roundup archive with natural language queries, returning sourced excerpts, issue details, and tool mentions. It supports hybrid semantic and keyword search, issue retrieval, and archive browsing with no API keys required.

Enables searching and retrieving documents from a local folder to ground LLM answers in your files.

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

Enables AI assistants to search a curated database of 200+ AI tool cards with pricing, platforms, use cases, and source links, so users can ask which tool to use for a task and get grounded recommendations.

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.