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.
-
Contextcoregithub.com/lucifer-ux/Contextcoreupdated this year
ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)
AGPL-3.0 ★ 22 -
rust-docs-mcp-servergithub.com/Govcraft/rust-docs-mcp-serverupdated this year
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
MIT ★ 301 -
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 .
-
A bridge from MCP to 9Router. Call 9Router's web search, web fetch, image generation, text-to-speech, speech-to-text, and embedding models as tools, over stdio or Streamable HTTP.
Apache-2.0 ★ 1 -
mddbgithub.com/tradik/mddbactive
Embedded knowledge base with 114 MCP tools, hybrid BM25+vector search and RAG. One Go binary.
NOASSERTION ★ 6 -
Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.
MIT ★ 59 -
Tool-agnostic long-term memory for LLM agents (HTTP API, MCP, CLI, embedded WebUI)
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 -
Video link to answers over MCP: downloads with audio merged, transcribes, embeds frames and transcript with jina-embeddings-v4, and returns typed, timestamped evidence with the frames. 19 typed tools, resources and prompts.
NOASSERTION -
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.
MIT ★ 60 -
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.
MIT ★ 37 -
Qdrant-MCPgithub.com/ncasfl/Qdrant-MCPupdated this year
CP server exposing Qdrant vector DB store and GPU-accelerated embedding pipeline as tools for Claude Code, Claude.ai, and OpenClaw.
MIT ★ 1 -
juju-mcpactive
JUJU — local-first MCP server with 74 coding, screen, media, speech, browser, game and workflow tools; embedded OAuth and owner-controlled workspace permissions.
npm MIT -
DODO — local-first MCP server with multi-project coding, AI providers, sub-agents, context, memory, media and workflow tools; embedded OAuth and workspace permissions.
npm MIT -
chartbrew-mcpgithub.com/dhavanikgithub/chartbrew-mcpupdated this year
Chartbrew + AI agents. MCP server exposing Chartbrew's documented API: teams, connections, datasets, dashboards, charts, live queries, and secure embedding. TypeScript · stdio · restricted/unrestricted tool modes.
MIT ★ 1 -
Model Context Protocol (MCP) server that provides AI agents with searchable access to any markdown content through resources and an embedded full-text search tools.
Apache-2.0 -
Universal, cross-tool persistent memory bank for AI assistants (Claude Code, Cursor, Windsurf, OpenCode, Codex) powered by FastMCP, Gemini embeddings & Supabase pgvector.
MIT ★ 5 -
Model Context Protocol server exposing the Champollion pipeline (MRI → sulcal embeddings) as tools: one per stage, a full-pipeline tool, job tracking and preflight checks.
NOASSERTION -
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 -
omni-coder-dashboardgithub.com/riko5652/ocdupdated this year
OCD (Omni Coder Dashboard) — An AI memory engine with real semantic embeddings, 21 MCP tools, cross-tool routing, trace auditing, and proactive IDE interception. 100% local, zero API keys required.
npm AGPL-3.0-or-later -
@iflow-mcp/abdrabdr-mcp-swarmgithub.com/abdrabdr/mcp-swarmupdated this year
Universal AI agent coordination platform with 35 smart tools, encrypted Vault, embedding cascade (Ollama/OpenAI/builtin), 6 vector backends, agent profiles, scheduled tasks, plugin system, and GitHub sync
npm MIT -
OCDgithub.com/Riko5652/OCDactive
OCD (Omni Coder Dashboard) v5.6.0 — AI memory engine with real semantic embeddings, 25 MCP tools, session guard, trace-to-evidence audit bot, Antigravity intelligence, cost visibility, smart routing, and proactive IDE interception. 100% local, zero API keys.
NOASSERTION ★ 3 -
json-mcp-liteno update data
Turn any JSON file (product catalogue, FAQ, price list) into a read-only MCP server. Exposes list, search and get tools over stdio. Keyword search, no embeddings, no API key, two dependencies. Works with Claude Desktop, Claude Code and Cursor. MIT.
smithery -
OpenEmbedded/Yocto layer for embedded lab automation with CI/CD runners, flashing tools, power control, hardware testing, remote access and Agentic AI automation.
NOASSERTION ★ 18 -
HippoBox is a unified FastAPI + FastAPIMcp for managing a personal knowledge base. It provides CRUD operations for knowledge entries, semantic search powered by embeddings, and MCP tool integration for use in Claude Desktop or other MCP-compatible clients.
MIT ★ 1 -
Ontology-driven codebase indexer and query service. Parses C#, TypeScript/JS, Go, Python, and SQL into an embedded graph database. Exposes Model Context Protocol (MCP) tools for AI agents to perform deep static analysis, cross-project call-graph tracing, and data lineage mapping.
MIT ★ 18 -
Python SDK + MCP server for Telys — embedded, on-device memory & retrieval for AI assistants. 19-tool MCP surface (io.github.thyn-ai/telys on the Official MCP Registry); the engine is a separate closed, signed on-device runtime — the SDK and MCP surface are Apache-2.0.
Apache-2.0 -
MCP stdio server exposing GNL docs to AI coding assistants (any MCP-compatible CLI/editor): overview/feature/search tools. Hand-written JSON-RPC 2.0 (no SDK), embedded static content + optional live gnl.dev fetch.
npm Apache-2.0 -
ragentgithub.com/ca-srg/ragentupdated this year
CLI tool for building production RAG systems from Markdown, CSV, and PDF documents using hybrid search (BM25 + vector) with OpenSearch. Features MCP server, Slack bot, Web UI, multi-source ingestion (local/S3/GitHub), and multi-provider embeddings (Bedrock/Gemini).
NOASSERTION ★ 13 -
Template Spring Boot 4 / Java 21 helpdesk API: one service and persistence layer behind three interfaces — JSON REST, binary Protobuf over plain HTTP, and an embedded MCP server with AI assistant tools. PostgreSQL 18, Flyway, Vault, Testcontainers.
MIT -
metcoregithub.com/hopenmind/metcoreupdated this year
Neural memory diagnostics engine based on the Markov Embedding Theorem (MET). Includes a Python library, a 17-tool Model Context Protocol (MCP) server for LLMs, and a cross-platform desktop GUI.
NOASSERTION -
An MCP server and Next.js web app for querying S&P 500 company data from Supabase, with tools for company info, news, officers, and SEC filings, plus embedded MCP App UI resources, Elicitation, and Sampling support.
AGPL-3.0 ★ 109 -
localgraphgithub.com/mehuljn/localgraphupdated this year
LocalGraph is a zero-dependency CLI tool written in Go that parses repositories into SQLite relationships (Imports, Definitions, Calls). It computes semantic embeddings locally using LM Studio or Ollama and serves codebase context directly to AI editors (Cursor, OpenCode) over the Model Context Protocol (MCP).
-
animica-mcpgithub.com/animicaorg/animica-mcpupdated this year
MCP server for the Animica post-quantum blockchain — 22 read/compute tools (chain reads, free AI inference + embeddings, quantum RNG, pool stats, notarisation, x402 catalog). No API key, no private keys. pip install animica-mcp / uvx animica-mcp; remote: https://mcp.animica.org/mcp
Apache-2.0 -
Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
npm MIT ★ 306 -
**Persistent memory for AI agents that you can actually read.** Kybase stores what your agent learns as plain Markdown notes with `[[wikilinks]]`, searched by keyword and by meaning. It runs locally: notes live in an embedded Postgres on your machine (`~/.kybase`), with no Docker, no server and no account. **What your agent gets (18 tools)** - **Search** — `search_notes`: hybrid keyword + semantic search that returns the section each excerpt came from - **Read** — `get_note` (whole, windowed or one section), `list_notes`, `list_tags`, `list_folders`, `indexing_status` - **Write safely** — `create_note`, `append_to_note`, `replace_in_note`, `update_note` with conflict protection, `delete_note` / `restore_note` (trash) - **Link** — `get_backlinks`, `get_neighbors`, `get_graph` over the wikilink graph - **Organize** — `create_folder`, `update_folder`, `delete_folder` **Setup** Keyword search works right away. For search by meaning, pick an embedding provider in the settings: local **Ollama** (`ollama pull embeddinggemma`) keeps everything on your machine; **Google** or **OpenAI** need an API key and send note text to that provider. **Your data stays yours** `kybase-mcp export vault.zip` writes every note out as plain Markdown, folders as directories, readable in any editor, Obsidian included. **Want a UI?** The full Kybase app adds a web editor, a knowledge-graph view, share links, and one memory shared by Claude Code, claude.ai and Cursor: [github.com/Kyrzin/kybase](https://github.com/Kyrzin/kybase) Open source, AGPL-3.0.
smithery -
Digital Samba Embedded API MCP Server
MIT ★ 1 -
Offline Polish↔English translation & terminology MCP server for LLM agents: Argos Translate MT, SQLite FTS5 dictionary lookup, bge-m3 + sqlite-vec translation memory. Air-gapped after install; every result carries source and license.
-
engram-memorygithub.com/EngramMemory/engram-memoryupdated this year
The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.
NOASSERTION ★ 39 -
Let your coding agent develop firmware on the real board, with the hardware as the gate.
pypi Apache-2.0 ★ 26 -
Professional Serial Port Debugging Assistant with Modbus, PLC, CAN, I2C/SPI support and MCP server
NOASSERTION ★ 41 -
让 LLM Agent 直接在线调试安卓设备 —— 抽象 adb / ssh / UART 多种传输,通过 MCP / CLI / Web API 三层接入大模型。
Apache-2.0 ★ 1 -
Deep code indexing for AI agents. SQLite FTS5 + tree-sitter + embeddings + MCP.
pypi MIT -
unchgithub.com/uchebnick/unchupdated this year
Local-first semantic code search for repository annotations via GGUF embeddings and sqlite-vec.
Apache-2.0 ★ 15 -
MCP server for semantic code search and codebase analysis — AST parsing, Tree-sitter, embeddings and vector search for AI assistants and LLMs
MIT ★ 3 -
YATS — Knowledge graph for AI coding agents. Cut code-reading tokens by 37–73%. Works with Codex, Claude, Copilot, Cursor & Gemini.
NOASSERTION -
Sistema de Memoria Dual MCP con Búsqueda Híbrida (SSC/BIRE) — PostgreSQL + pgvector + pg_trgm + embeddings locales (Ollama)
MIT ★ 5 -
MCP server + CLI for AI-native SEO audits: broken links, internal link suggestions, crawl diffs, optional local embeddings.
MIT ★ 2 -
Serial port MCP server for Claude Code, Codex, Opencode and AI agents. Reliable UART/USB-serial access for embedded development.
MIT ★ 20 -
High-performance, SIMD-accelerated vector search engine and MCP server for .NET 10. Optimized for LLM embeddings and semantic search.
MIT ★ 6 -
Semantic code search for AI agents and CLI users. CLI + MCP server using local ONNX embeddings — no API keys, no external services.
★ 1 -
—
MIT -
claude-code-memorygithub.com/d2a8k3u/claude-code-memoryupdated this year
A Claude Code plugin that gives Claude fully automatic, per-project cognitive memory with hybrid search, session lifecycle hooks, and local embeddings.
MIT ★ 8 -
Local-first AI agent memory for coding projects: SQLite context, MCP server, Codex skill, Rust CLI, and optional embeddings.
Apache-2.0 ★ 1 -
embspec-mcpgithub.com/MukundaKatta/embspec-mcpupdated this year
MCP server: embedding pipeline ops + drift detection for production RAG. Assert query encoder matches index manifest; compute retriever stability between two index versions. Wraps embspec.
MIT -
descrygithub.com/jKiler/descryupdated this year
Local hybrid (vector + BM25) code search for AI coding agents — AST chunking, MiniLM embeddings on ONNX, Go call graph, MCP server. No external services.
Apache-2.0 ★ 1 -
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.
MIT ★ 9 -
A Visual Studio Code extension that connects to embedded Linux devices over SSH, tails their logs, and displays them with loglevel colorization, filtering presets, custom keywords highlighting and filtered export.
MIT ★ 3 -
Engramgithub.com/Artemarius/Engramupdated this year
GPU-accelerated local semantic code index for Claude Code. CUDA-powered embeddings, HNSW vector search, tree-sitter AST chunking, MCP server — sub-3ms queries, fully on your machine.
★ 1 -
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.
MIT