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.
-
computer-use-plusgithub.com/Ethanout/computer-use-plusupdated this year
Low-token, low-latency Windows computer-use MCP with learned shortcuts, UIA/CDP/OCR routing, and DeepSeek Harness support
MIT ★ 3 -
Siglagithub.com/apkd/Siglaactive
Low-latency code search MCP server for Rust, C# and Unity projects
MIT ★ 2 -
Sym-MCPgithub.com/Eis4TY/Sym-MCPupdated this year
A secure, low-latency SymPy MCP server for agents/LLMs, with AST + runtime sandboxing, process pool prewarming, and compact JSON outputs for reliable auto-retry workflows.
pypi MIT ★ 2 -
sphero-rvr-mcpgithub.com/jsperson/sphero_rvr_mcpupdated this year
MCP server for controlling Sphero RVR with Claude AI - featuring direct serial protocol for low-latency control
pypi MIT -
A fast, low-latency Rust-based Model Context Protocol (MCP) server querying local rustdoc JSON via SQLite FTS5 for AI agents.
MIT ★ 1 -
fernandesgithub.com/tranlybuu/fernandesupdated this year
Unified Android automation hub & FastMCP server featuring low-latency live streaming, interactive web console, and UI annotation/OCR for AI agent control.
-
Low-latency graph memory for AI agents — indexed W5H graph, SQLite, hooks/MCP for Claude Code, Cursor and Copilot, live dashboard
pypi MIT -
rust-mcp-azuregithub.com/zubeyralmaho/rust-mcp-azureupdated this year
Rust MCP server on Azure Container Apps — an azd template for memory-safe, low-latency agent tool execution
MIT -
jarvis-eyes-mcpgithub.com/harshil1502/jarvis-eyes-mcpupdated this year
macOS-native MCP server for low-latency desktop awareness — accessibility tree + screenshots + window navigation. TypeScript + Swift hybrid.
MIT -
multimodal_search_mcp_architecturegithub.com/estelacode/multimodal_search_mcp_architectureupdated this year
Low-Latency Multimodal Search Web App with MCP Architecture 🔌🛠️🧠 #StrandsAgentSDK #FasterWhisper #Multilingual #MultimodalSearch #ChromaDB # DockerCompose
★ 1 -
Serverless PayPal MCP integration on Cloudflare Workers. Handles API requests, auth, and secure payments with low latency via Cloudflare's edge. Ideal for webhooks, payment verification, and real-time transactions. Scalable, lightweight, and secure.
Apache-2.0 ★ 7 -
WebRTC MCP Server — peer-to-peer multi-agent communication, room-based signaling, and video stream bridging via low-latency DataChannels.
npm MIT -
Scalable MCP backend optimized for Claude Code and Claude Desktop — secure, low-latency, plug-and-play.
MIT ★ 3 -
AI-learning-coach-MCPgithub.com/TechMaverickHub/AI-learning-coach-MCPupdated this year
AI Learning Coach MCP + Streamlit Dashboard (Supabase + Groq + pgvector) A full-stack Learning Coach system built using: Supabase (pgvector) for content storage, semantic search & embeddings Groq LLM (llama3.1-8b-instant) for fast, low-latency digest generation SentenceTransformer (all-MiniLM-L6-v2) for embedding generation
MIT -
Andrea---AI-Healthcare-Receptionistgithub.com/ShreyKamdar0503/Andrea---AI-Healthcare-Receptionistupdated this year
Andrea is a production-ready, multi-agent voice AI receptionist for a dental clinic, built using VAPI, GPT-4o-mini, n8n workflows, and an MCP server. It handles real-world phone conversations including appointment scheduling, intake, insurance checks, and call logging with low latency and high reliability.
-
High-performance, low-latency MCP server for local code context. Features AST-aware symbol graphs, semantic reranking, and PageRank-scored search for AI agents (Claude, Cursor, and more).
NOASSERTION ★ 6 -
Low-latency Rust prediction-market trading bot for Kalshi & Polymarket (crypto, sports, politics). 12 autonomous strategies (Momentum, Maker, Arbitrage, ML, etc.), real-time Next.js Control Tower, and an AI LLM Advisor that delivers optimization recommendations via Ollama (local or remote), MCP + Telegram and OpenClaw.
AGPL-3.0 ★ 37 -
weather-mcp-a2agithub.com/Ratnesh-181998/weather-mcp-a2aupdated this year
MCP-based agentic AI system enabling LLMs to fetch and reason over real-time global weather data using standardized tool invocation. Built with MCP Server/Client, Llama 3, and external APIs to deliver low-latency, hallucination-free weather intelligence through protocol-driven workflows.
MIT ★ 1 -
nft-mint-agentgithub.com/dhasap/nft-mint-agentupdated this year
⚡ Competitive multi-wallet NFT auto-minting agent for OpenSea/SeaDrop & direct contracts — low-latency fast-mint (raw EIP-1559, multi-RPC fan-out, RBF), scheduled drops, browser fallback & listing. Runs as an MCP server, an AI-agent skill (Hermes/Claude), or a CLI. Security-hardened, multi-chain EVM.
MIT ★ 6 -
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
go MIT ★ 931 -
token-scoutgithub.com/jackccrawford/token-scoutupdated this year
For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.
MIT ★ 9 -
scrcpy-mcpgithub.com/JuanCF/scrcpy-mcpno update data
scrcpy-mcp gives AI agents real vision and control over Android devices. It exposes screenshots, taps, swipes, text input, key events, UI inspection, and arbitrary ADB shell commands as MCP tools, so an agent can drive a phone or tablet the way a person would. When a scrcpy session is active, input and screen capture run 10–50× faster than plain ADB, making real-time automation, on-device testing, and UI agent workflows practical. Highlights - Fast screenshots and live screen capture - Tap, swipe, drag, long-press, scroll, and text input - UI hierarchy dump and element search by text, resource-id, or class - Arbitrary ADB shell command execution - Optional scrcpy session for low-latency control Works with any ADB-reachable Android device (USB or Wi-Fi). Configure ADB_PATH, ANDROID_SERIAL, and scrcpy paths as needed.
smithery -
Open source Rust daemon that diagnoses tail latency on Linux, applies verified fixes and rolls them back if they don't help. Open rules, CLI and MCP for AI agents.
Apache-2.0 -
High-throughput MCP server for real-time FinTech market telemetry, exposing 13 financial tools over stdio and SSE transports.
-
bolttx-mcp-servergithub.com/BoltTx-io/bolttx-mcp-serverupdated this year
MCP server for BoltTx — submit Solana transactions through any MCP-compatible AI agent
MIT -
A Model Context Protocol server exposing NinjaTrader 8 market-structure state to an MCP client, with the NinjaTrader AddOn that feeds it. By The Boy Prodigy for Obsidian Flow.
Apache-2.0 -
Options trading and research system in C++23: one event-driven engine for backtest and live trading on Interactive Brokers, a quant lab on the same data, and MCP tools for AI agents.
Apache-2.0 ★ 29 -
Rust + WASM sublinear-time solver for asymmetric diagonally dominant systems. Exposes Neumann series, push, and hybrid random-walk algorithms with npm/npx CLI and Flow-Nexus HTTP streaming for swarm cost propagation and verification.
npm MIT ★ 94 -
MCP server: which AI model is up, fast, popular or low-priced right now. Public data, no API key. Node 18, zero deps.
npm MIT