Search and retrieval (RAG) MCP servers

1,794 servers

Index your own content and search it by meaning (retrieval-augmented generation, RAG).

Filter and sort these servers

Start from the first servers

@devpuccino/mcp-qdrant org.bitbucket.devpuccino/mcp-qdrant

MCP Server for Qdrant Vector Database - Search, manage collections, and points

Version check not run yet

Search and retrieval (RAG) npm Local MIT
@iflow-mcp/raintree-technology-docpull io.github.raintree-technology/docpull-mcp

MCP server for fetching and searching documentation with semantic search

Version check not run yet

Docs and knowledge bases npm Local MIT
r2mcp io.github.dmokong/r2mcp

Persistent semantic memory layer for Claude Code — PostgreSQL + pgvector + OpenRouter embeddings

Version check not run yet

Search and retrieval (RAG) npm Local 52 a week MIT
@sniper.ai/mcp-knowledge io.github.virkt25/sniper-mcp-knowledge

SNIPER MCP server for domain knowledge indexing and retrieval

Version check not run yet

Search and retrieval (RAG) npm Local MIT
mcp-recall io.github.sakebomb/mcp-recall

Context compression and persistent retrieval for Claude Code

Version check not run yet

Memory and context npm Local 50 a week MIT
@a13xu/lucid io.github.a13xu/lucid

Token-efficient memory, code indexing, and validation for Claude Code agents — SQLite + FTS5, TF-IDF + Qdrant retrieval, AST skeleton pruning, diff-aware context, Logic Guardian drift detection

Version check not run yet

Search and retrieval (RAG) npm Local 49 a week MIT
@jayarrowz/mcp-arsr io.github.jayarrowz/mcp-arsr

Adaptive Retrieval-Augmented Self-Refinement MCP Server — a closed-loop system that lets LLMs iteratively verify and correct their own claims using uncertainty-guided retrieval.

Version check not run yet

Search and retrieval (RAG) npm Local MIT
llmemory io.github.entaina/llmemory

Memory infrastructure for agents: short-term checkpointing, long-term file-based and graph-based memory, retrieval with time decay, and maintenance jobs.

Not checked yet

Files and storage RubyGems MIT
ctxloom-pro io.github.kodiii/ctxloom-readme.md

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with token-efficient Skeletonization.

Version check not run yet

Developer tools npm Local 44 a week SEE-LICENSE-IN
light-mem io.github.devestacion/light-mem

Lightweight persistent memory for Claude Code and OpenCode. In-process embeddings, no external services.

Version check not run yet

Memory and context npm Local 44 a week APACHE-2.0
@hyperterminal-ai/mcp-server io.github.hyperterminal-ai/hyperterminal-mcp-server

MCP server for Hyperterminal — real-time AI news, semantic search, and weekly digests for AI agents.

Version check not run yet

Web search and scraping npm Local MIT
Velocirag io.github.HaseebKhalid1507/velocirag

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

Version check not run yet

Search and retrieval (RAG) Official MCP Registry Local
@iflow-mcp/guangxiangdebizi-web-retrieval-mcp io.github.guangxiangdebizi/web-retrieval-mcp

一个专门用于解析网页设计结构的MCP工具

Version check not run yet

Search and retrieval (RAG) npm Local APACHE-2.0
@lotargo/memory_plugin io.github.lotargo/memory_plugin

Local-first memory, hybrid RAG, and agent personalization for AI coding agents (OpenCode, Claude Code, Codex, Gemini CLI, Antigravity). MCP server + CLI with persistent context, document ingestion, ve

Version check not run yet

Search and retrieval (RAG) npm Local 41 a week MIT
@ssmeo/mcp-local-rag io.github.g0spel/mcp-local-rag

Local RAG MCP Server - Easy-to-setup document search with minimal configuration (fork with remote embedding server support)

Version check not run yet

Search and retrieval (RAG) npm Local 41 a week MIT
@teknologika/mcp-codebase-search io.github.teknologika/mcp-codebase-search

Local-first semantic codebase search for AI coding assistants using MCP, Tree-sitter parsing, and LanceDB vector storage

Version check not run yet

Developer tools npm Local 41 a week MIT
github-rag-mcp io.github.liplus-project/github-rag-mcp-mcp-server

MCP server for semantic search of GitHub issues/PRs via Cloudflare Worker

Version check not run yet

Git and code hosting npm Local 40 a week APACHE-2.0
wide-researcher io.github.jaivial/wide-researcher

Qdrant-backed semantic code-search, AST/symbol graph search, and impact-radius diagrams for Claude Code MCP.

Version check not run yet

Developer tools npm Local 40 a week MIT
traqr-memory-mcp io.github.jiggycapital/traqr-oss-memory-mcp

Memory-as-a-service MCP server for AI agents. 12 tools, Postgres + pgvector, multi-strategy retrieval. Works with Claude Code, Cursor, Codex, and any MCP client.

Version check not run yet

Memory and context npm Local 39 a week FSL-1.1-ALV2
@porast1/mcp-cognitive io.github.porast1/mcp-cognitive

Universal MCP server for AI knowledge persistence with Weaviate hybrid search

Version check not run yet

Search and retrieval (RAG) npm Local MIT
Solitaire for Agents io.github.PRDicta/solitaire

Identity infrastructure for AI agents. Evolving persona, session continuity, self-tuning retrieval.

Version check not run yet

DevOps and infrastructure Official MCP Registry Local
remembrallmcp io.github.roboticforce/remembrallmcp

Persistent knowledge memory and code dependency graph for AI agents - Rust, Postgres, pgvector, MCP

Version check not run yet

Developer tools PyPI · crates.io Local MIT
Picsha AI ai.picsha/picsha

AI-native digital asset management: semantic search, generative image edits, and CDN delivery.

100% up · 30 days

Design and media Official MCP Registry · npm Local Remote ISC
SmartMemory ai.smartmemory/smartmemory-mcp

Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.

Version check not run yet

Memory and context Official MCP Registry · PyPI Local MIT
graphx io.github.timmikeladze/graphx

Temporal GraphRAG on libSQL/SQLite, Postgres, or DuckDB — typed schema, bitemporal graph, vector + FTS retrieval, a served HTTP API, React Query hooks, and an MCP server

Version check not run yet

Databases npm Local 35 a week MIT
htm io.github.madbomber/htm

HTM (Hierarchical Temporal Memory) provides intelligent memory/context management for LLM-based applications. It implements a two-tier memory system with durable long-term storage (PostgreSQL) and tok

Not checked yet

Memory and context RubyGems MIT
embarsy-qdrant-mcp io.github.arsenyganov-pixel/embarsy-embedder-embarsy-qdrant-mcp

Codebase-indexing MCP server for Embarsy — semantic code search over a local Qdrant + OpenAI-compatible embeddings stack. Routes embeddings and Qdrant through Embarsy's proxy so auth and Monitoring co

Version check not run yet

Search and retrieval (RAG) npm Local 31 a week POLYFORM-STRICT-1.0.0
Webshift io.github.x-hannibal/webshift

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

Not checked yet

Web search and scraping Official MCP Registry · crates.io
cortex-rag io.github.ravikantiakshay/cortex

Codebase Intelligence Engine & MCP Server — AST semantic chunking, tri-hybrid retrieval (BM25 + vectors + graph), and grounded LLM synthesis for any repository.

Version check not run yet

Search and retrieval (RAG) npm Local 30 a week MIT
Factcheck io.github.carlisia/mcp-factcheck

An MCP server that validates content against MCP specification using semantic search and AI

Version check not run yet

Search and retrieval (RAG) Official MCP Registry · Go modules Local MIT
@dfine-io-gmbh/semantic-mcp io.github.dfine-io/dfine-semantic-mcp

Semantic code search MCP server: embeds a project into a local SQLite vector store for natural-language queries.

Version check not run yet

Developer tools npm Local 29 a week MIT
agent-illustrator io.github.egyjs/agent-illustrator-mcp-server

Vector illustration engine for LLM agents, served over MCP.

Version check not run yet

Design and media npm Local 29 a week MIT
@kelabome/skillbase io.github.kelabome/skillbase

Find agent skills by meaning, not keywords: local semantic search over shared git skill repos for Claude Code, Codex and OpenCode. An MCP server that keeps any number of skills out of your agent's con

Version check not run yet

Git and code hosting npm Local 28 a week MIT
better-qdrant-mcp-server io.github.wrediam/better-qdrant-mcp-server-5rpvp2

MCP server for enhanced Qdrant vector database functionality

Version check not run yet

Search and retrieval (RAG) npm Local 28 a week MIT
justbetter-mcp io.github.igiamronit/justbetter-mcp

An MCP gateway with dynamic, retrieval-based tool injection.

Version check not run yet

Search and retrieval (RAG) npm Local 28 a week MIT
mnemex io.github.madappgang/mnemex

Seven-layer code memory — benchmarked. AST-aware chunking, symbol graph with PageRank, semantic + BM25 retrieval. Personal, team-shared, offline-first, any embedding or LLM provider. MCP server + CLI.

Version check not run yet

Search and retrieval (RAG) npm Local 28 a week MIT
@199-bio/engram io.github.199-biotechnologies/engram

Give Claude a perfect memory. Local-first MCP server with hybrid search.

Version check not run yet

Memory and context npm Local 56 a week MIT
agent-memory-store io.github.vbfs/agent-memory-store-bf7rwj

Shared, persistent memory for teams of AI agents over MCP. Hybrid search (SQLite FTS5 + local multilingual embeddings), safe for many agent processes, zero external services.

Version check not run yet

Memory and context npm Local 27 a week MIT
budget-aware-mcp io.github.doorman11991/budget-aware-mcp

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tre

Version check not run yet

Search and retrieval (RAG) npm Local 25 a week MIT
toolscope-ts io.github.0xjord4n/toolscope-ts

Semantic tool retrieval for TypeScript agents, powered by Bun

Version check not run yet

Search and retrieval (RAG) npm Local 25 a week APACHE-2.0
@sapmcp/sap-search-mcp io.github.saurabh-chothe/sap-search-mcp

SAP Test Case Search MCP Server - Search and retrieve SAP test cases from Azure AI Search vector database

Version check not run yet

Search and retrieval (RAG) npm Local MIT
Embgrep io.github.ArkNill/embgrep

Local semantic search — embedding-powered grep for files, zero external services.

Version check not run yet

Search and retrieval (RAG) Official MCP Registry Local
@hyperlynq/synaptic io.github.hyperlynq/synaptic

Persistent local memory for Claude Code — cross-session context recall, semantic search, zero cloud

Version check not run yet

Memory and context npm Local 23 a week SEE-LICENSE-IN
getlore io.github.hyunjae-labs/lore-06psce

Semantic search MCP server for Claude Code conversation sessions

Version check not run yet

Search and retrieval (RAG) npm Local 23 a week MIT
midbrain-memory-mcp io.github.midbrainai/midbrain-memory-mcp

Persistent experience for coding agents: episodic capture and semantic search

Version check not run yet

Coding agent tools npm Local 23 a week MIT
@copilotkit/pathfinder io.github.copilotkit/pathfinder

The knowledge server for AI agents — index docs, code, Notion, Slack, and Discord into searchable, agent-accessible knowledge via MCP. Supports OpenAI, Ollama, and local transformers.js embeddings.

Version check not run yet

Docs and knowledge bases npm Local 22 a week ELASTIC-2.0
@erichare/astra-mcp io.github.jestatsio/astra-db-plugin-server

Unofficial JEStats integration for Astra DB: live database tools, interactive views, guarded writes, vector and hybrid search, data-modeling skills, and Data API examples in five languages.

Version check not run yet

Search and retrieval (RAG) npm Local 22 a week APACHE-2.0
@headwood/rag-hub-mcp io.github.openhoat/rag-hub-mcp

RAG Hub MCP — knowledge bases by folder, exposed via MCP + REST. Uses Ollama/Bifrost/OpenAI-compatible embeddings + SQLite/FTS5.

Version check not run yet

Search and retrieval (RAG) npm Local 22 a week MIT