"All items" matching MCP servers:

Agent memory on a local SQLite file or on PostgreSQL with pgvector, with provenance, trust verdicts and explicit abstention when memory cannot support an answer.

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

Enables any MCP client to index files, directories, and arbitrary text into a local SQLite-backed vector database and perform semantic search with language-aware chunking, filters, and context expansion, all offline without network calls.

Enables AI agents to parse PDFs and search local document context through multimodal extraction and vector-based retrieval, all exposed as MCP tools.

Memory for facts that change. A retrieved record is marked SUPERSEDED, with when a later record replaced it, so an assistant does not answer with a value that is no longer true. Single file, numpy the only dependency, runs with a local embedding model or none at all.

Enables Claude Desktop and compatible agents to search, read, add, update, and delete a locally stored, user-curated memory using hybrid retrieval with reranking and Qdrant. All processing runs locally without cloud services or API keys.

Enables Claude to build and query a local, folder-based knowledge base with hybrid vector and BM25 search, save and edit notes, ingest Markdown/text folders with source citations, and browse or restore version history — all running embedded on a laptop with no server or API key.

Enables semantic search across Apple Mail, Messages, Calendar, and Contacts on macOS using natural language queries. All processing happens locally with privacy-first vector indexing for fast similarity search.

Enables vector search and document retrieval from pipelines, text extraction and chunking of files into Markdown, and private deep research generation, all backed by Vectorize.

A self-hosted second brain MCP server that enables capturing thoughts with deduplication and semantic search using local embeddings and PostgreSQL with pgvector, all running on your own hardware.

Local-first semantic memory layer for MCP agents. Recall, remember, forget, stats over stdio. ChromaDB plus sentence-transformers, all on-machine.

txtai is an all-in-one embeddings database for semantic search, LLM orchestration and language model workflows. All functionality can be served via it's API and the API supports MCP. Docs: https://neuml.github.io/txtai/api/mcp/

Enables coding agents to persistently store memories, artifacts, and context discarded by compaction into a searchable store, then automatically recall and inject the items relevant to the current task. It fuses BM25 keyword search with embedding-vector retrieval so differently-phrased memories still match, running as a fail-open sidecar that never blocks the agent session.

Gives multiple AI coding agents a shared, persistent memory by indexing your code and documentation into a vector database with AST-aware chunking and hybrid semantic/keyword search. Agents can search across projects and store, update, or forget decisions, conventions and lessons learned, all self-hosted with local embeddings.

Enables AI assistants to semantically search your entire local conversation history from Claude Desktop, ChatGPT and Claude Code, and to retrieve, browse, ingest and report on those conversations. All embeddings run locally, so no cloud, API keys, or data leave your machine.

Enables AI agents to maintain persistent, multi-layer cognitive memory with vector search, deterministic verification, experiment tracking, and cost-aware recall, all through 87 MCP tools and a local Flask UI.

Local podcast transcription, embedding, and semantic search with an MCP server for AI assistant integration. All processing runs on your machine.

A local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically.

A very simple vector store that provides capability to watch a list of directories, and automatically index all the markdown, html and text files in the directory to a vector store to enhance context.

Enables MCP clients such as Cursor, Claude, and Windsurf to store and recall user preferences, behaviors, and other text-based information across conversations, using vector similarity search so conceptually related items are found even when exact keywords differ.

An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded

Kollektiv

A personal knowledge MCP server with vector database for the Opencode ecosystem. It enables semantic search, tag organization, and session memory logging, all running locally without external API keys.

A retrieval-only MCP server that searches a vectorized Wangsu Terraform Provider documentation knowledge base and returns relevant snippets with rules to guide the caller's LLM in generating accurate, provider-specific answers. It offloads all inference to the calling client, as it does not invoke any LLM or require API keys on the server side.

Enables LLM-based agents and MCP-compatible clients such as Claude Desktop to perform full CRUD operations on FHIR resources, manage documents with semantic vector search and a RAG-ready pipeline, and look up standardized LOINC terminology, all through natural-language prompts. It connects to FHIR-compliant backends like Medplum with OAuth2 authentication and supports Docker or uv deployment.

Provides a per-project memory layer with plain notes, semantic vector recall, and a knowledge graph, all hosted on Cloudflare's free tier. It includes a web dashboard for browsing projects and deleting them.

Enables AI assistants to search and query PDF documents through a local RAG system with vector embeddings. Provides semantic document search capabilities while keeping all data stored locally without external dependencies.

Enables LLM clients to chat with locally indexed markdown engineering documentation through semantic search, keeping all indexing and retrieval on-device for privacy.

Enables coding agents to share a persistent local memory store across sessions and clients, saving, searching, updating, and retrieving facts, decisions, incidents, preferences, references, and snippets with semantic and lexical search.