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.
-
Digital Samba Embedded API MCP Server - Model Context Protocol server for Digital Samba's Embedded API
npm MIT -
Digital Samba Embedded API MCP Server
npm MIT ★ 1 -
Fast-Embedding-MCP-SSEgithub.com/Rikka-Botan/Fast-Embedding-MCP-SSEupdated this year
Fast static text embeddings via OpenAI-compatible API & MCP server. English, 16M params, Matryoshka 512→32D.
Apache-2.0 -
neuroencoderactive
EEG embeddings API client, CLI and MCP server for EPI-300K, an EEG foundation model
pypi Apache-2.0 -
A self-hosted embedding server with HTTP, gRPC and MCP APIs, verified model installation, batching, health checks, metrics and Windows and Linux releases.
Apache-2.0 ★ 5 -
Local-first embedding server (ONNX on-device or API) — the reference /embed server for CPersona. MIT.
pypi MIT ★ 1 -
URL → RAG-ready Markdown in one API call: heading-aligned chunks, embeddings, change-aware re-indexing, docs crawler + llms.txt, MCP server. Free tier.
-
Document image retrieval via MCP or API for agentic systems using semantic embeddings, YOLO, and VLM classification.
NOASSERTION ★ 4 -
MCP server exposing NaN API media tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
npm MIT ★ 12 -
MCP server for Forge, Voxell's hosted text-embedding API (Turbo/Pro/Ultra, OpenAI-compatible)
npm MIT ★ 1 -
nexusbridge-mcp-servergithub.com/guhank/nexusbridge-mcp-serverupdated this year
MCP server for NexusBridge — a unified AI API brokerage. Access 200+ AI models and 10 service categories (LLM chat, code generation, image generation, embeddings, web search, document parsing, sentiment analysis, translation, summarization, code execution
npm MIT -
cognee-mcp-fastembedgithub.com/Lauredmarin/cognee-mcp-fastembedupdated this year
cognee-mcp with local fastembed embeddings (no external embedding API)
-
Self-hosted agentic RAG for multi-repo code intelligence: real ASTs (Roslyn/TSC/Pyright) → semantic knowledge graph (SQLite + sqlite-vec) → SGC graph convolution → REST + embedded MCP server. Local embeddings, zero external APIs.
★ 1 -
MCP server for Alibaba Cloud DashScope: Qwen chat, embeddings and model discovery with your own API key.
Apache-2.0 ★ 9 -
engramgithub.com/bmbnexus/engramupdated this year
Persistent memory for Claude Code — 6 MCP tools, SQLite, local embeddings, zero API calls. Your AI remembers across sessions.
npm ★ 5 -
Long-term memory for AI agents: hybrid-searched memories over human-editable markdown notes. 100% local — offline ONNX embeddings, SQLite FTS5, MCP server, REST API, CLI, dashboard. No cloud, no API keys.
npm ISC -
Obsidian plugin that surfaces semantically related notes and semantic search using local or API embeddings, with an MCP server.
GPL-3.0 ★ 22 -
qdrant2github.com/neco001/qdrant2updated this year
Universal Qdrant MCP server with automatic dimension detection and search integrity. Supports any OpenAI-compatible embedding API (OpenAI, Qwen, Gemini, Ollama).
MIT -
Tool-agnostic long-term memory for LLM agents (HTTP API, MCP, CLI, embedded WebUI)
MIT -
MCP server for ByteDance Volcano Engine -- text generation, multi-turn chat, and embeddings via Doubao LLM models (Volcano Ark API)
npm MIT -
knowledge-base-servergithub.com/SalvatierraPM/knowledge-base-serverupdated this year
Self-hosted persistent memory for AI agents. Shared brain for Claude, ChatGPT, Gemini via MCP + REST API. SQLite FTS5, local embeddings, Obsidian sync.
MIT -
Semantic code search for AI agents and CLI users. CLI + MCP server using local ONNX embeddings — no API keys, no external services.
nuget ★ 1 -
Euro-Argo float metadata + OSO ontology in one Elasticsearch index, embedded for RAG and served via an HTTP API and an MCP server.
Apache-2.0 -
Universal RAG: pipeline plugable de RAG con conectores universales (texto, archivos, URLs — audio/video próximamente), embeddings locales, ChromaDB y respuestas con citas verificables. API + CLI + MCP.
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 -
ponymemorygithub.com/ponytech-dev/ponymemoryupdated this year
Autonomous 5-tier memory system for Claude Code — Qdrant semantic search + Obsidian knowledge archive + local BGE-M3 embeddings. Zero API keys, fully local.
★ 1 -
Production embedding & decision inference service in Rust — Candle/ONNX dual engine, CUDA/Metal acceleration, REST/gRPC/MCP/CLI generated via sdforge, rerank, Matryoshka dimensions, OpenAI-compatible API, and semantic caching
Apache-2.0 ★ 1 -
Truly Zero-Dependency Advanced MCP server with local file-based memory features for VS Code/Cursor - NO EXTERNAL API REQUIRED - Built-in AI embeddings using native algorithms - Zero-config local semantic search (Embedding v1.2.0, FileSystem v2.0.0, Memory
npm MIT -
obenan-api-clientstale
MCP server implementation for Obenan API with embedded Python code
npm ISC -
Personal memory for Claude Code and Codex. Save links, notes, and files from inside the agent; find them later by describing what you remember. Local SQLite + embeddings, no API key.
npm 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 -
needlegithub.com/alexandremourin/needleupdated this year
Semantic code search MCP server: tree-sitter chunking + local Model2Vec embeddings + BM25/dense hybrid (RRF). Hands an AI only the relevant code (file:line), ~10-100x fewer tokens. Multi-language, no API key.
MIT -
Search your team's entire Discord from Claude in ~1s. Keeps a local SQLite index (FTS5 + embeddings) because Discord's search API is closed to bots.
MIT ★ 1 -
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 -
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.
MIT ★ 1 -
The most advanced MCP memory server. Hybrid search (BM25 + jina v5 embeddings + cross-encoder rerank), 100+ languages, temporal knowledge graph, finds any past Cursor or Claude conversation from a vague description, signed automatic updates. Pure Rust, single binary, 100% local, zero API calls.
mcpb NOASSERTION ★ 18 -
Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.
oci WTFPL ★ 6 -
Local MCP server for semantic code search. AST-aware chunking with tree-sitter, offline ONNX embeddings, hybrid vector + BM25 (RRF) ranking, one SQLite file. No API keys or cloud. Semantic code search for Claude Code, Cursor, opencode and AI coding agents.
npm MIT -
Give your coding agent the right code, not more code. Local context engine for Claude Code, Cursor & Codex: code graph + hybrid search + embeddings + git history, packed into a token budget. Held-out SWE-bench: right file in 4k tokens 92% vs 29% for search + whole files. MIT, no API keys.
pypi MIT -
Kiro MCP Power that gives Kiro long-term memory. Indexes all CLI and IDE conversations into a semantic search engine using local or API-based embeddings. Newest-first indexing, leader-follower coordination, multi-computer fan-out search, and instant cosine similarity search. This makes Kiro weird and sci-fi like...
NOASSERTION -
MCP server for OpenAI ChatGPT API — chat, vision, and embeddings
-
MCP client for Obsidian Local REST API with embedded Rust server
-
MCP server for Revit API documentation and The Building Coder blog. No API keys, no embeddings, Revit not required.
MIT -
MCP server for xAI Grok API — chat, vision, search, and embeddings
-
Self-hosted REST + semantic search API for Obsidian Markdown vaults, with local embeddings, MCP and a web dashboard.
MIT ★ 3 -
The API workbench that embeds in your own service. gRPC, REST, GraphQL, MQTT, SignalR, WebSocket, MCP and more - embedded in ASP.NET or as a standalone CLI.
nuget Apache-2.0 ★ 12 -
Pure Rust API gateway built on Pingora, with safe traffic draining, immutable config changes, scoped MCP tools, and an embedded admin console.
Apache-2.0 ★ 1 -
iwsdk-rag-mcpgithub.com/felixtrz/iwsdk-rag-mcpupdated this year
MCP server providing semantic code search and API reference for the Immersive Web SDK using RAG (Retrieval-Augmented Generation) with vector embeddings
npm MIT ★ 2 -
AI-native web crawler and structured data extraction engine - one Rust binary with CLI, embedded dashboard, REST API and MCP server for AI agents.
MIT ★ 5 -
gemini-mcp-servergithub.com/salviz/gemini-mcp-serverupdated this year
MCP server with 23 tools for Google Gemini API — chat, multimodal analysis, deep research, YouTube, Files API, embeddings, and more
MIT ★ 1 -
bitbadges-builder-mcpgithub.com/bitbadges/bitbadges-builder-mcpupdated this year
MCP server for building BitBadges collections with embedded documentation and API tools
npm MIT -
A fully local MCP server providing AI agents with persistent semantic long-term memory using SQLite and transformer-based embeddings. No cloud dependencies or API keys required.
npm MIT ★ 2 -
Component lookup over the encode-ui shadcn registry, as an MCP server. Zero setup; local embeddings, no API keys.
npm MIT -
code-indexgithub.com/hdimer/code-indexupdated this year
Semantic code search as an MCP server. Find code by meaning, not keywords. Local embeddings + Milvus Lite, no API keys.
MIT -
MCP server for a team's model & service catalog (vLLM, embeddings, custom services) with REST API and web UI
MIT -
This is an unofficial Model Context Protocol (MCP) server that provides various AI capabilities using the DeepInfra OpenAI-compatible API, including image generation, text processing, embeddings, speech recognition, and more.
★ 2 -
Perplexity MCP server and CLI in Python: Agent, Search, Embeddings and Decisions APIs, model routing, local chat history, usage and cost tracking
npm MIT ★ 3 -
you-need-an-advisor-mcpgithub.com/senivel/you-need-an-advisor-mcpupdated this year
MCP server that gives AI assistants full YNAB API access with embedded budgeting methodology for informed financial guidance
pypi MIT ★ 1 -
mollygraphgithub.com/brianmeyer/mollygraphupdated this year
Embedded local-first graph and vector memory for AI agents, with Ladybug storage, GLiNER2 extraction, and MCP/API/SDK access.
★ 1 -
Atlasgithub.com/sidmanale643/Atlasupdated this year
A Python semantic-memory framework with SQLite storage, optional vector search and local embeddings, plus optional CLI, API, MCP, and web adapters.
★ 1