MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
@iflow-mcp/priyankgodhat-etabs-mcp-server-local-embeddingsupdated this year
MCP server for ETABS documentation using local embeddings
npm ISC -
MCP Server using local embeddings to search user-provided ETABS documentation.
MIT ★ 16 -
Claude Context MCP with EmbeddingMonster support - Local embeddings, dual-model architecture, and race condition fixes
npm MIT -
@iflow-mcp/patakuti-local-knowledge-rag-mcpupdated this year
Local Knowledge RAG MCP Server - Semantic search and retrieval for local documents using vector embeddings
npm MIT -
local-MCP-RAGgithub.com/manali2304/local-MCP-RAGupdated this year
The MCP tool can then be used inside VS Code / MCP-enabled clients to search local internal documentation using natural language. Uses persistent embedding using minilm-l6-v2, supports multi format embedding and semantic retrieval .
-
Local-first embedding server (ONNX on-device or API) — the reference /embed server for CPersona. MIT.
pypi MIT ★ 1 -
rag-localgithub.com/MauricioPerera/rag-localupdated this year
Local-first RAG memory for LLMs: Node server with ONNX embeddings, OKF-structured chunks, portable vector bundles, and REST + Web UI + CLI + MCP interfaces
MIT -
Local RAG MCP Server - Easy-to-setup document search with minimal configuration (fork with remote embedding server support)
npm MIT -
mcp-ai-braingithub.com/nawkarpravinp-bit/mcp-ai-brainupdated this year
Local-first persistent memory for AI agents. SQLite + hybrid search (keyword + local vector embeddings). Zero API costs. Works with Claude, Cursor, Windsurf, and any MCP-compatible agent.
npm MIT -
pdf-rag-mcpgithub.com/AstralApart/pdf-rag-mcpupdated this year
Local PDF RAG MCP server with SiliconFlow embeddings.
MIT -
An MCP server exposing local embedding tools - semantic search, comparison, clustering and zero-shot classification - so an agent can call them in a loop without an API round trip. Caching the embeddings took a search from 1040ms to 1.2ms. PyTorch, sentence-transformers, MCP Python SDK v2.
MIT -
Local-first memory for coding agents: MCP server, single SQLite file, local embeddings
mcpb MIT ★ 10 -
svdb-mcpgithub.com/localpoid/svdb-mcpupdated this year
Local semantic search over your Markdown files, exposed to an LLM as an MCP server. Embeddings run on Ollama.
MIT ★ 1 -
multimodal-embedding-mcp-servergithub.com/Hafizzowa/multimodal-embedding-mcp-serverupdated this year
Build a Local Multi-Modal AI Agent Memory Server Using Gemini Embeddings 2026
-
Long-term memory for AI agents. MCP server with local embeddings, heat-based recall, and hierarchical clustering on embedded SurrealDB.
AGPL-3.0 ★ 4 -
UI App for ChromaDB to build local RAG pipelines. Built for macOS, native Swift. Gives you full control over embedding for RAG.
MPL-2.0 ★ 2 -
Local-first context ingestion and retrieval for AI tools. SQLite + embeddings + MCP server for Cursor & Claude.
AGPL-3.0 ★ 43 -
codebase-memorygithub.com/H-Gelender/codebase-memoryupdated this year
MCP memory server for codebase analysis: embedding-based retrieval + clean-code analysis (local-first, scalable to low-end machines).
-
rag-vaultgithub.com/maxrotemberg04-spec/rag-vaultupdated this year
Local-first RAG over my Obsidian vault — hand-rolled hybrid retrieval (BM25 + embeddings + RRF), cited answers, MCP server for AI agents.
MIT -
unchgithub.com/uchebnick/unchupdated this year
Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.
go Apache-2.0 ★ 15 -
pythiagithub.com/michaeljboscia/pythiaupdated this year
Local-first code & knowledge retrieval framework for AI agents: incremental indexing, semantic + lexical search, MCP server, pluggable embedding backends.
NOASSERTION -
Local, private "where did I write that?" search for your notes, built for coding agents: BM25 + local Ollama embeddings, MCP server, disk-verified results.
MIT ★ 1 -
A MemPalace fork with flexible self-hosted embeddings, transcript-aware long-chat mining, stronger Chinese support, and stdio MCP integration for local AI clients.
MIT ★ 1 -
Local-first semantic code search for AI coding agents. Index projects with Ollama embeddings, store searchable context in SQLite, and retrieve relevant code through a local MCP server.
NOASSERTION -
Obsidian plugin that surfaces semantically related notes and semantic search using local or API embeddings, with an MCP server.
GPL-3.0 ★ 22 -
ai-labgithub.com/bunlongheng/ai-labupdated this year
Local-first RAG second brain - key-free embeddings, SQLite vector store, Obsidian ingestion, MCP server for Claude Code
MIT -
semantic-search-mcpgithub.com/zulaxy/semantic-search-mcpupdated this year
Semantic code search MCP server for AI coding agents (opencode, Claude, Cursor). Local embeddings, no API keys.
npm MIT -
mcp-rag-servergithub.com/agarwalvishal/mcp-rag-serverupdated this year
MCP RAG server — local embeddings, your docs never leave your machine. Private knowledge base + web search for Claude, Cursor, and Ollama. Drop your docs, connect your AI client, done.
MIT ★ 6 -
JS-PotatoRAGgithub.com/MauricioPerera/JS-PotatoRAGupdated this year
Consola RAG local air-gapped + memoria para agentes (MCP). Base vectorial cuantizada en 3 bits (Rust/WASM, ~21x), embeddings ONNX y LLM locales, PWA instalable.
MIT -
mcp-recallgithub.com/YanpengQi7/mcp-recallupdated this year
Local-first structured memory for Claude Code over MCP — semantic recall of incidents, code reading, decisions, and lessons. SQLite + sqlite-vec, local embeddings, no API keys.
★ 1 -
Local-first memory for AI agents. SQLite, hybrid keyword and semantic search, Ollama or OpenAI embeddings, an MCP server, a CLI, and a local web UI.
npm Apache-2.0 ★ 1 -
Local, session-aware memory archive for Hermes Agent: numpy + sqlite + local Ollama embeddings, served to agents over MCP.
MIT -
Minimal local RAG MCP server: semantic search over your markdown docs, embeddings via Ollama, nothing leaves your machine.
npm MIT -
Search your C# codebase by meaning, not keywords. 100% local - Ollama embeddings + SQLite vectors + MCP server. No cloud, no telemetry.
MIT ★ 7 -
gemini-embedding-2-mcp-servergithub.com/AlaeddineMessadi/gemini-embedding-2-mcp-serverupdated this year
🚀 A powerful Model Context Protocol (MCP) server powered by Gemini Embedding 2. Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents! 🔎✨
MIT ★ 5 -
Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings.
-
mychatarchivegithub.com/1ch1n/mychatarchiveupdated this year
Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and search via MCP server. Zero cloud, zero cost.
NOASSERTION ★ 72 -
A local knowledge base for AI agents. Search, cite, and manage documents through MCP, with Qdrant, Qwen3 embeddings, and a web UI.
MIT -
linux-time-machinegithub.com/rbryce90/linux-time-machineupdated this year
Local-first Linux observability with historical scrubbing, semantic journald search, and an MCP server for Claude-driven investigation. Go + SQLite + Ollama embeddings.
MIT -
Local OpenAI-compatible embeddings and reranking on Apple Silicon: bge-m3 hybrid search, Qwen3, a retrieval eval harness and MCP memory for agents.
MIT ★ 1 -
kxgithub.com/distu/kxactive
Local-first MCP server and CLI for AI coding agents. Hybrid semantic + BM25 search across code, docs and notes, with SQLite and offline embeddings.
MIT ★ 5 -
Local-first AI agent memory for coding projects: SQLite context, MCP server, Codex skill, Rust CLI, and optional embeddings.
Apache-2.0 ★ 1 -
ostk-recallgithub.com/os-tack/ostk-recallupdated this year
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
Apache-2.0 ★ 6 -
Cortex - local-first persistent memory for AI coding agents (MCP server + HTTP API, SQLite, hybrid FTS5 + local embeddings)
npm MIT -
engramgithub.com/HBarefoot/engramupdated this year
🧠 Persistent memory for AI agents. SQLite for agent state. Zero cloud dependencies. Local embeddings. MCP-native integration with Claude Desktop/Code, Cursor, Windsurf & more.
npm MIT ★ 9 -
cc-historygithub.com/Straska7/cc-historyupdated this year
Local-first, cross-session memory for Claude Code, with redaction before embedding. Recall a procedure, decision or answer from any past session, in any other.
Apache-2.0 -
qa-memorize-mcpupdated this year
RAG-based memory MCP server with local ONNX embeddings
npm MIT -
Local-first knowledge base with hybrid search (vector + BM25) and knowledge graph, powered by embedded SurrealDB and BAAI/bge-m3 — exposed as MCP server and CLI
MIT -
embedbasegithub.com/jaymeklein/embedbaseupdated this year
Local-first document embedding and retrieval platform with a REST API and MCP server for LLM agents. Supports hybrid BM25 + semantic search across workspaces and collections, with pluggable parsers, embedders, and vector stores.
★ 1 -
@adamrdrew/agent-memory-mcpgithub.com/adamrdrew/agent-memory-mcpupdated this year
MCP server for persistent agent memory — hybrid BM25 + vector search backed by LanceDB with local ONNX embeddings. No API keys, fully local.
npm GPL-3.0-or-later -
mcp-server-qdrantgithub.com/vaporif/mcp-server-qdrantupdated this year
Rust MCP server for Qdrant with local embeddings (Candle/ONNX)
cargo MIT -
Semantic search over your own code, documents and git history, for coding agents over MCP. One container on your machine: local embeddings with Ollama, hybrid search with Qdrant, and a web UI.
Apache-2.0 -
wrongsynapsegithub.com/ersinkoc/wrongsynapseupdated this year
Local-first Cognitive Memory Operating System and MCP server for autonomous AI coding agents. Tri-hybrid retrieval: ONNX semantic embeddings + SQLite FTS5/BM25 + hierarchical knowledge graph, fused with Reciprocal Rank Fusion. Zero cloud.
npm MIT -
Cerebro — shared, attributed memory for AI agent teams, with the Sinapsis web panel: hybrid search, local embeddings (EmbeddingGemma), tasks and MCP. Runs fully local.
MIT ★ 1 -
Cross-harness requirements registry and Agile board for coding agents: MCP server, CLI and local web board backed by SQLite with local embeddings.
npm Apache-2.0 -
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB. Nothing leaves your machine.
pypi MIT ★ 60 -
@grumppie/ownsearchgithub.com/grumppie/ownsearchupdated this year
Text-first local document search MCP server backed by Gemini embeddings and Qdrant.
npm MIT -
satchel-raggithub.com/virgilvox/satchelupdated this year
Portable RAG system on a USB drive. Single binary, local embeddings, MCP protocol.
cargo MIT -
Persistencegithub.com/sjsam/Persistenceupdated this year
Local, provider-agnostic MCP memory server — save an AI chat's context in one tool and recall it in another. SQLite + sqlite-vec with local Ollama embeddings.
MIT -
Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.
pypi MIT ★ 37