"SearXNG - Open Source Metasearch Engine" matching MCP servers:

Long-term persistent memory for AI agents with hybrid search (DiskANN + FTS), bi-temporal knowledge graph, and 81.1% LongMemEval accuracy.

Stores what AI agents learn — thoughts, decisions, session events and repo facts — in PostgreSQL with pgvector and serves it back through versioned MCP tools with hybrid vector-plus-full-text retrieval and budgeted context packs. Enables multiple agents to share one scoped, role-isolated long-term memory, with deliberate promotion of distilled candidates into durable memories.

Enables MCP clients to index code repositories and run AST-aware semantic and hybrid keyword search across files, commits and branches, returning relevant code snippets with expanded file context. It handles incremental re-indexing with local embeddings and Qdrant storage, and can serve either over stdio or as a bearer-token-protected HTTP endpoint for remote or containerized use.

Open-source MCP server for mem0 that enables memory storage and retrieval using local LLMs, self-hosted, and Docker-free.

An ultra-rational A2A protocol for zero-token edge pre-filtering and FEP-driven deadlock prevention. Uses Cloudflare Vectorize (384d cosine similarity) with a 24h deposit model, restricting bargaining to a 4-rally limit before forcing HTTP 402 dimension jumps.

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.

Enables unified access to SQL, semantic vector search, and columnar analytics through a single MCP interface.

A read-only Model Context Protocol server that exposes a semantic knowledge base to AI agents via 27 tools. It enables querying of documents and data integrated from sources like Notion, SharePoint, HubSpot, and Slack.

A remote MCP server enabling semantic memory across multiple AI platforms like Perplexity Comet and Claude Desktop, with vector embeddings for intelligent retrieval.

Enables managing knowledge bases in Open WebUI and retrieving relevant fragments from Qdrant-stored knowledge through an MCP client.

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.

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

Connects AI agents to Teradata databases for querying, analysis, administration, and AI pipelines with enterprise security.

Enables Claude to retrieve and reason over internal business documents, client histories, and SOPs stored in ChromaDB for hallucination-free, context-aware responses.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Official Telys MCP server: private, on-device AI memory and retrieval powered by native Mojo kernels. 19 tools: memory CRUD, semantic + BM25 search, single-key filters, compaction/IVF/tuning and self-refreshing repo auto-indexing. Stdio. Introspection needs no credentials; execution requires a one-time free telys login. Source: packages/telys-sdk/telys/mcp.py. Registry: io.github.thyn-ai/telys.

Local-first, source-traceable memory for AI agents — no LLM at ingest, $0 per message, zero data egress. Gives Claude Code, Cursor, and any MCP client one shared persistent memory with semantic recall, belief revision, selective forgetting, and a provenance guard that blocks acting on stale or unconfirmed memories.

Enables semantic retrieval over locally indexed PDF manuals and books, exposing tools to list available sources and search excerpts by query with page, chapter, source, and relevance metadata.

A Model Context Protocol (MCP) server that provides a local-first RAG engine for your markdown documents. It uses a file-based Milvus vector database to index your notes, enabling LLMs to perform semantic search and retrieve relevant content from your local files.

Local-first agent-memory MCP server with a why() tool: recall a fact together with its connected subgraph (multi-hop), so linked memories surface even when they share no words with the query. remember/recall/relate/forget/why over one fused vector + graph + columnar engine a single offline Rust binary.

Local-first knowledge retrieval MCP server that turns private text documents into a source-backed knowledge base, enabling retrieval, comparison, summaries, and review outlines for any local MCP client while keeping source paths and index operations visible.

Connects AI assistants to a persistent memory engine with Neo4j knowledge graph and ProMem extraction, enabling long-term context and associative memory across chats and workspaces.

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 retrieval-augmented question answering over Obsidian vaults and document folders, with local embeddings, vector search, and cited source paths.

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Enables an LLM to maintain and query durable layered context across sessions, retrieving standing rules, current state, open loops, compiled pages, historical facts, and hard records with explicit conflict handling and abstention when nothing matches.

Headless geometric memory engine for AI agents — no Vector DB, no cloud, no API key. Store and retrieve by meaning using native Vector Symbolic Architecture (NVSA) math over O_DIRECT NVMe mapping. Runs entirely on your machine via MCP.

Mem0-compatible persistent memory for AI agents - write facts once, recall them semantically in any session. Self-hostable open-source server, or managed cloud with a remote MCP endpoint at https://deepmem.dev/mcp.

Enables GitHub Copilot Chat to semantically search locally indexed source code, documentation, and project statistics from reference projects through a fully local vector store. This lets Copilot find existing implementations and conventions so it generates new code homogeneous with established patterns, without any API keys or data leaving the machine.

Exposes a shared graph-based context engine as MCP tools for Claude, Copilot, and other AI agents, enabling knowledge ingestion, recall, search, and LLM-ready context assembly across sessions.