"A tool for reading PDF files" matching MCP servers:

Exposes semantic search over a folder of indexed PDF guides as a tool that Claude Code or any MCP client can call. Returns the closest matching passages with relevance scores, source file and page citations, so the client can answer questions about the guides while knowing when nothing relevant was found.

A Model Context Protocol server that enables AI agents to read, search, and extract content from PDF 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 Model Context Protocol (MCP) server that provides powerful RAG (Retrieval-Augmented Generation) capabilities for PDF documents. This server uses ChromaDB for vector storage, sentence-transformers for embeddings, and semantic chunking for intelligent text segmentation.

A Python-based MCP server that enables document-based question answering by processing PDF, TXT, and Markdown files through OpenAI's API. It provides hallucination-free responses based strictly on document content using semantic search and includes a web interface for management.

Enables secure read-only access to Tencent Lexiang knowledge bases via MCP, including listing directories, RAG search, and reading entries.

Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying.

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

Enables AI agents to provide e-commerce customer service with product search, RAG-based FAQ answers, human handoff, and automated security auditing with a review workflow.

Enables intelligent ingestion and querying of PDF, Markdown, and text files using hybrid search that combines keyword matching and semantic embeddings with citations.

Provides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.

Rust-powered PDF toolkit over MCP: create, read, and analyze PDFs; extract text and entities for RAG; convert to Markdown; split/merge/rotate/reorder pages; manage form fields and annotations; encrypt documents. Runs locally via uvx oxidize-mcp.

Indexes local documents (PDF, Word, Markdown, text) into a SQLite database for AI agents to search and retrieve bounded, source-located passages. Runs fully locally with optional OCR, preserving privacy.

On-premises knowledge retrieval over the Markdown, text, PDF, Word and Excel files an organization keeps, with the rules you set enforced before anything is retrieved. Agents connect over MCP, get cited passages, and read from it and never write to it.

An Operit-compatible adapter of the Exa MCP server, enabling web search, code search, and company research capabilities in AI assistants. It fixes MCP handshake compatibility issues, allowing tools like web_search_exa and web_fetch_exa to load and run reliably.

Simple, fast, long-term memory for your AI chatbots, agents, and MCP tools. Give your LLM a persistent memory using a local SQLite file. No complex database servers, no heavy cloud setup, and zero C++ compilation errors. Works everywhere.

Enables AI agents to convert files, render web pages to markdown/PDF/screenshots, search the live web, extract structured data, ingest RAG-ready chunks, and monitor pages for changes through a single API key.

Four utilities in one server: PDF text, ruled tables and OCR from a URL as pages, documents or RAG chunks; YouTube thumbnail URLs and files with per-size availability; sports scores, schedules and standings across 33 leagues; and ATP/WTA tennis with per-set scores and draws.

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.

A stdio MCP server that provides a single tool to query Gemini with Google Search grounding for current web information, returning synthesized answers with source links.

Enables local-first hybrid knowledge retrieval from authorized Markdown and plain-text files, combining full-text and vector search with reranking and traceable source references via a single search tool.

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.

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.

An MCP server that indexes a repository locally and provides keyword, semantic, hybrid, and SQL search tools, enabling coding agents to answer questions about the codebase efficiently without reading files one by one.

Enables a persistent local library for mathematical PDFs with cached LaTeX extraction, full-text search in English and Greek, and page/image retrieval over MCP.

A local-first MCP server that ingests PDFs, extracts structure, and provides semantic search and sequential navigation tools for AI clients to query and learn from documents.

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 exposing lease Q&A via the lease_qa tool, querying a LeaseClear API to return grounded answers about specific lease documents.

Enables natural-language search over locally indexed files such as markdown, text, images, videos, and PDFs, and retrieves indexed text or media metadata by path. It lets Cursor query a local embedding index built with Gemini and SQLite.

Search your own files from Claude & any MCP client: PDF, Office and more. Exact full-text search with page numbers, 100% local. Needs the RootMind app.