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.
-
@vaur94/mcp-codegithub.com/vaur94/mcp-codeupdated this year
Production-grade MCP server for semantic coding workflows and AI coding-agent acceleration.
npm MIT -
Every startup opportunity in India — grants, accelerators, incubators, gov schemes & more. With an AI agent MCP server.
MIT ★ 1 -
A native GPU-accelerated terminal for autonomous multi-agent teams. Run 20+ CLI agents with in-memory tracking, guarded PTY, 38+ native MCP tools, Git Worktree isolation & Project collaboration. 100% local-first, zero telemetry, no cloud gates on macOS, Windows & Linux.
AGPL-3.0 ★ 1 -
GPU-accelerated Linux desktops in Docker/WSL2 for AI agents and humans, featuring a built-in 60-tool MCP server and browser access.
GPL-3.0 ★ 2 -
Local GPU-accelerated visual runtime for coding agents: an MCP server and CLI that render JSON scenes to PNG/GIF.
Apache-2.0 -
Automate and accelerate complex projects. Fast, effective, and consistently structured. MCP server, Claude Skills, CLI. JSON output available for AI agents.
npm MIT ★ 5 -
MLX-Powered Agentic RAG System implementing Anthropic's Code execution with MCP pattern, featuring Claude Code hooks, skills, and MLX acceleration with Qwen3-VL-2B-Thinking for enhanced reasoning
-
Zero-loss Markdown & LaTeX translation engine with Apple Silicon (MPS) / CUDA acceleration, CLI, CI/CD, and Model Context Protocol (MCP) for AI Agents.
MIT -
search-meshgithub.com/jamestkelly/search-meshupdated this year
SIMD-accelerated, single-pass codebase intelligence fabric for AI agents. Offload multi-keyword scans and AST context-pruning to native silicon.
MIT ★ 3 -
PathViewgithub.com/PABannier/PathViewupdated this year
PathView is a high-performance whole-slide image viewer for digital pathology. PathView combines GPU-accelerated tiled rendering with polygon overlays for cell segmentation visualization and AI agent integration via the Model Context Protocol (MCP).
★ 4 -
AI Agent wrappers for Life Sciences APIs (Open Targets, ChEMBL, UniProt). Accelerating drug discovery with Model Context Protocol (MCP) and FastMCP.
MIT ★ 9 -
High-performance Rust MCP browser runtime for AI agents, built on Chromium/CDP with DOM interaction, screenshots, GPU/WebGPU acceleration, live browsing, media, authentication, security guards, and automatic Chrome runtime updates.
-
Local, version-aware code & docs search with hybrid retrieval and reference graphs for your AI coding agent, accelerated with Rust
pypi MIT -
EpisodAI by Lalith Alpuri, also written Alpuri Lalith (@lalithbuilds): a local AI-agent memory MCP server with SQLite WAL, hybrid retrieval, Obsidian workflows, an HTTP bridge, and hardware-aware acceleration.
MIT ★ 1 -
MCP server, CLI, and TUI for reading and sending iMessage / SMS on macOS — lets AI agents text humans, fetch conversation history, and stream-export entire chats. Includes a self-healing watchdog and an optional Rust acceleration module.
npm MIT -
Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs. Fused semantic + SIMD-accelerated hybrid recall, in-process MCP, REST/gRPC, and language SDKs.
npm Apache-2.0 ★ 28 -
Native, GPU-accelerated interface design tool built in Rust. Opens and saves .fig files, runs your own coding agent on the open file, ships an MCP server. FREE + source-available (PolyForm Shield).
NOASSERTION ★ 95 -
grepaigithub.com/vp2722/grepaiupdated this year
🔍 GrepAI - Local AI-powered codebase search MCP Server. Self-hosted MCP server with GPU-accelerated LLM support (llama.cpp/vLLM). Search, analyze, and navigate your codebase with Claude Code or any MCP-compatible AI agent. One-command installation.
MIT -
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.
pypi MIT ★ 59 -
USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with skills and autonomous agents.
MIT ★ 211 -
Production-grade Unified MCP Server architected to bridge enterprise n8n automation with agentic LLM ecosystems. Engineered for high-scale reliability with structured logging, multi-transport support (SSE/STDIO), and context-aware orchestration. Accelerating AI-native business infrastructure via secure, deterministic, and scalable workflow control.
-
dhm-hybridgithub.com/emircbngl/dhm-hybridupdated this year
Open-source digital holographic microscopy (DHM) workstation: off-axis hologram reconstruction, quantitative phase imaging, autofocus, and reference-free phase retrieval via a hybrid classical + CNN pipeline. PySide6 GUI, optional Apple Silicon MLX acceleration, and an MCP server for AI agents.
Apache-2.0 ★ 1 -
Peridot v1.6.0 [STABLE] | Sovereign AI Kernel. Offline, GPU accelerated Qwen framework: a 27B model fully on an 8GB GPU at 23.6 tok/s. Sandboxed skills & plugins, model tool use, opt in web search, MCP bridge for private data jobs from cloud agents, ZAT-SCS preemption, RAG. Zero data exfiltration. Engineered by uncoalesced.
MIT ★ 8 -
100,000+ AI briefings in 41 categories: models, dev tools, agents, research, funding. New briefings are fact-checked against their source post and link to it. Plain Markdown, CC BY 4.0. MCP server + Agent Skill let Claude, Cursor or VS Code ask for the latest. Signals tracks what is accelerating. Read at blogs.drix10.com
npm CC-BY-4.0 ★ 132 -
Hardened Liferay DXP Integration SDK for Batch, Workflow, and API orchestration.
-
lab-ops-acceleratorgithub.com/pvenkata-tech/lab-ops-acceleratorupdated this year
Production AI agent for genetic testing lab exception handling. Features LangGraph orchestration, MCP-based LIMS/EHR integration, RAG protocol retrieval, and HITL review
-
Open-source AI business platform for customers, sales, delivery, billing and marketing. Self-host it and build workflows on shared records and permissions.
MIT ★ 1 -
自托管多服务加速网关:Docker / GitHub / HuggingFace 一站加速,多用户隔离、Token 鉴权、磁盘缓存与镜像搜索;内置 MCP,AI Agent 友好。
MIT ★ 3 -
Free, universal MCP tools that help Claude, Codex, and other AI hosts find and prepare Buffalo/WNY opportunity registrations.
MIT -
Hardware-adaptive local LLM & cloud cascading gateway. Sub-5ms intelligent routing, 3-token lookahead failover, asymmetric verification, 1-click IDE config, and MCP for $0 token cost.
MIT ★ 4 -
A production-grade, MCP-compliant agentic forecasting tool. Designed for Agentic AI orchestrators to autonomously resolve inventory shortages, evaluate demand risk, and execute quantile-bounded supply-chain decisions—without requiring local fine-tuning.
MIT -
Heinzelmännchen: helpers accelerating product teams with a CLI, web UI, and MCP tools — like the little elves from Cologne.
MIT ★ 2