"Finding MCP servers with high ratings and no API key required" matching MCP servers:

Open-source MCP servers for ESG data extraction, analysis, and regulation management, providing 31 tools across 6 servers for tasks like metrics extraction, PDF processing, vector storage, and web scraping.

Provides retrieval-augmented generation (RAG) capabilities by ingesting various document formats into a persistent ChromaDB vector store. It enables semantic search and retrieval using either OpenAI or Ollama embeddings for processing local files, directories, and URLs.

Enables storing and retrieving text in a local vector store using Qdrant, running fully locally with no external database or API key.

Persistent AI memory server with 3-layer hybrid search (vector + FTS5 + keyword), confidence scoring via Reciprocal Rank Fusion, episodic/profile memory, and 16 tools. Zero LLM dependency. Works standalone with Claude Desktop and Claude Code. MIT licensed.

Facilitates knowledge graph representation with semantic search using Qdrant, supporting OpenAI embeddings for semantic similarity and robust HTTPS integration with file-based graph persistence.

Enables semantic search over OpenAPI endpoint catalogs using FAISS and LangGraph, returning grounded technical recommendations for natural-language API queries.

This server enables semantic search capabilities using Qdrant vector database and OpenAI embeddings, allowing users to query collections, list available collections, and view collection information.

Enables stateless similarity search over pre-computed vector corpora using NMI and cosine fusion with entropy-calibrated weighting. Provides tools for ranking, scoring, outlier detection, and alpha calibration for AI agents.

Enables hybrid search (BM25 + semantic with RRF) over documentation, with Thai language support. It exposes MCP tools for adding documents and searching via Qdrant and Ollama/OpenAI, using a stateless Streamable HTTP transport.

Enables bidirectional synchronization of vector database collections between local and remote Qdrant instances with tools for comparison, dry-run previews, and sync operations in both directions.

Local-first memory for Claude Code and any MCP client: hybrid vector + keyword search and a bi-temporal knowledge graph in one SQLite file. Local embeddings, no API key, $0/token.

Enables natural language search and analysis of uploaded PDF, CSV, and Excel documents using retrieval-augmented generation and MCP tools, providing contextual answers to user queries.

Local offline semantic search over documents (txt, md, pdf, docx, pptx, csv). Indexes folders into a LanceDB vector database with multilingual embeddings and supports hybrid vector + keyword search via Reciprocal Rank Fusion. No API keys, no cloud, no Docker required.

Enables AI clients to store and semantically recall durable memories across sessions and tools, with local-first privacy and no API key needed.

MCP server for a self-hosted RAG system that enables AI tools to search and retrieve grounded answers from locally ingested documents via MCP tools, with local embeddings and no API key required.

Enables searching and asking questions over your PDF documents using a Pinecone vector index with local embeddings and language model, no external LLM API key required.

Enables semantic search and conversational querying across a personal research library of PDFs, DOCX, and other documents using a vector database. It provides tools for document summarization, finding related papers, and high-accuracy retrieval for AI clients like Claude Desktop.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

Provides AI assistants with long-term semantic memory capabilities through local vector-based storage. Enables storing, recalling, and managing information across sessions with complete privacy using ChromaDB, with no data ever leaving your machine.

Enables AI agents to interact with an embedded graph database (GrafeoDB) via the Model Context Protocol, providing tools for graph CRUD, GQL queries, full-text and vector search, and graph algorithms.