"How to create draft emails using Gmail's support agent class" matching MCP servers:

Enables a support bot to answer FAQ questions from a local vector store, with admin tools to add, list, and delete knowledge entries while enforcing read-only versus admin bearer-token permissions.

MCP server that ingests PDF documents into pgvector for semantic search and RAG pipelines. It handles extraction, chunking, local embeddings, and storage, enabling agents to make PDFs searchable via natural language.

A local-first knowledge base for LLM coding agents that indexes repository documentation, concept ontology, and build targets into Qdrant and exposes retrieval as MCP tools (search, get, list sources, reindex).

A self-evolving RAG system that enables AI agents to autonomously read and write memory, continuously learning and adapting user preferences, daily logs, and knowledge graphs across applications.

Gives MCP clients persistent personal memory and a versioned skill library, letting agents store facts, preferences, and decisions and recall them through hybrid semantic-plus-keyword search with automatic time weighting. Everything runs inside Cloudflare's free tier, with no server or database to operate.

A benchmarking MCP server that stores facts as both vector RAG and a knowledge graph, enabling head-to-head comparison of memory retrieval methods.

Enables hybrid search over policies using Reciprocal Rank Fusion and provides grounded, context-aware answers via a LangGraph agent with COSTAR prompting.

Enables external clients to query a vector knowledge base about skills and roles through an MCP retrieval tool, supporting RAG-based question answering with tool-calling.

Enables AI agents to maintain long-term, cross-session memory by extracting facts, reconciling state conflicts, and retrieving relevant memories via vector search.

A lightweight RAG system that provides an MCP server for searching and interacting with vector-based knowledge bases. It enables users to perform retrieval-augmented generation and search across Qdrant collections through a standardized interface.

Semantic skill-library search MCP server that finds relevant skills or Markdown knowledge files from local directories using embeddings, SQLite vector storage, and Reciprocal Rank Fusion.

Provides persistent memory for AI coding agents, enabling them to save, search (hybrid vector/BM25/concept graph), list sessions, and forget memories via MCP tools.

Retrieval-only MCP server that turns any knowledge source (Obsidian vault, notes, reference sets) into searchable Qdrant-backed skills, exposing list_skills, search_vault, and search_skill tools for agents to query via stdio or SSE.

Enables AI agents to store and recall durable facts, decisions, and lessons over MCP using hybrid semantic and keyword search, typed memories, graph relations, sessions, and time-travel queries. Runs locally with no server process or API key, persisting everything to files that both agents and a CLI can share.

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

MCP server that provides secure read-only access to a local folder, enabling file listing, reading, semantic search (RAG), and indexing status via natural language, integrated with Claude Desktop and a custom agent loop.

Enables AI agents to search and analyze clinical trial data from ClinicalTrials.gov using both structured SQL queries for filtering trials by status, phase, and conditions, and semantic vector search for exploring detailed protocol information like exclusion criteria.

Integrates R2R (Retrieval-Augmented Generation) with Claude Desktop, enabling semantic search across knowledge bases and RAG-based question answering with support for vector, graph, web, and document search.

Provides persistent memory management for AI agents with 14 tools, including semantic search, context synthesis, auto-context middleware, and write-back actions to external services like Slack.

Enables AI agents to read, write, organize, and link persistent long-term memory across model providers using embeddings and pgvector retrieval.