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.
-
AI browser automation. Write async Python to navigate, click, type, and extract data.
pypi -
Understand This Video For Me AI Plugingithub.com/africaappstudio-max/understand-this-video-mcpno update data
Let your AI watch and hear a video: key frames, transcript and contact sheet, processed locally.
mcpb -
Complete MCP server for Git and GitHub automation - installable globally with npm
npm MIT -
MCP server for consulting with AI models via OpenRouter
npm MIT -
MCP server for AI-powered image generation with ChatGPT and HuggingFace integration
npm MIT -
Vision MCP server that provides AI-powered image and video analysis using Google Gemini and Vertex AI
npm MIT -
@glgio/know-megithub.com/glgio/know-meupdated this year
AI package for developer portfolios — chat widget + MCP server, queryable profile from a single know-me.yaml.
npm MIT -
geolocate-me-mcpupdated this year
MCP server for Geolocate Me — query your GPS location from AI assistants
npm MIT -
Reach anyone's AI agent at their fone.me link — MCP server for ChatGPT, Claude, Cursor and more
-
ask-me-maybeupdated this year
Ask Me Maybe — an MCP server that enables AI assistants to ask humans questions via Slack, with extended timeouts and partial message support. Forked from trtd56/AskOnSlackMCP.
npm MIT -
@supermagicapps/remind-me-mcpupdated this year
MCP server for the Remind Me reminders platform. Gives AI agents the ability to create reminders, schedule messages, and manage settings.
npm -
Your AI assistants don't know who you are. mcp-me fixes that: a local MCP server that gives any AI a full picture of who you are
npm MIT ★ 21 -
Connect an AI assistant to the smart-me energy platform: meters, load profiles, EV charging and ZEV billing. Remote MCP server.
-
Lucky Me Clipper: AI-driven horizontal-to-vertical (9:16) video clipper & adaptive reframer with Swiss Design 2.0 Control Center, dynamic CSS/JS captions, and Agent Skills
-
A context provider on how I program. Basically the AI version of me.
npm MIT ★ 2 -
QueRegalar.me: wishlists your AI agent can actually use (WebMCP)
MIT -
Model Context Protocol (MCP) server for Trade Me API - enables AI assistants to interact with New Zealand's largest online marketplace
★ 6 -
thatsme-mcp-issuergithub.com/thatsmeapp/thatsme-mcp-issuerupdated this year
MCP server for That's Me issuers — issue certificates and track engagement via AI
npm MIT -
intel-asrai-mcpupdated this year
MCP server for AI-powered web search via intel.asrai.me with x402 micropayments on Base
npm MIT -
Ask your AI assistant about me: Anshul Panigrahi's portfolio as an MCP server (profile, projects, patents, contact).
npm MIT -
An MCP server for AI agents to interact with https://alexjef.net and https://t.me/alexjefBot VPN network
★ 2 -
Official SpeedOf.Me MCP server: run real internet speed tests from AI agents. Ships as the @speedofme/mcp npm package.
npm ★ 1 -
axiomgithub.com/sixthkind/axiomupdated this year
unifier.me is an open technology for use within personal ai agent stack. It filters your data vault on a per request basis. Available as mcp server too.
GPL-3.0 -
Remote MCP server that lets any AI agent send a real fax — no API key, pay per fax. Endpoint: https://faxer.me/mcp
MIT -
Prepare 360Score.me for AI workflows with a PipMCP setup doctor, authenticated discovery and coding-agent instructions.
MIT -
blogPublisherMCPgithub.com/singhkunal2050/blogPublisherMCPupdated this year
Blog Publisher MCP Server that lets me publish blogs from my AI Assitants, Detailed Blog here https://singhkunal2050.dev/blog/building-a-blog-publisher-mcp-server-automate-your-content-workflow-with-claude/
★ 2 -
I'm MeshSeeks, look at me! 🟦 A multi-agent mesh network for parallel AI task completion
npm MIT -
Jarvis-AI-Powered-Personal-Executive-Agentgithub.com/MITHELESH-45/Jarvis-AI-Powered-Personal-Executive-Agentupdated this year
My personal AI Digital Twin that understands my portfolio, answers questions about me, and autonomously performs real-world tasks using Agentic AI, Advanced RAG, MCP, Gemini, OpenAI, and Google Workspace integrations.
★ 1 -
DBT skills plus Let Them / Let Me for your AI assistant: a public, read-only MCP server on Cloudflare Workers
Apache-2.0 -
lovieme-mcpactive
Official Model Context Protocol (MCP) server for LovieMe — claim free *.lovie.me subdomains, configure Anycast DNS, and wire up cloud presets directly from AI coding agents.
npm MIT -
SVG Me for AI agents: remote MCP server and Claude Code plugin to convert images (including AI-generated ones) to SVG, PDF, EPS or DXF.
MIT -
AI agent for my Gmail: sorts emails, flags what needs me and drafts replies, using several Claude models, my own MCP server and a FastAPI web page.
★ 1 -
Clinical Root Cause Analysis MCP Server - AI-guided structured RCA with Fishbone (6M), 5-Why, and HFACS-MES integration for healthcare quality improvement
Apache-2.0 ★ 1 -
自托管的多人记账与结算 · Self-hosted group expense splitting with live sync, AI assistant and remote MCP. One-click deploy to Cloudflare Workers or Docker. 在线演示 / Live demo: aapay.lyjw.me
MIT -
MCP server + CLI for Employed by Guaq AI (jobs.guaqai.me) - thin Node launcher around the stdlib-only Python client, so `npx employed-mcp` works with no manual download.
npm MIT -
Turn how you work into an AI digital twin: a Markdown persona pack → a one-file MCP server, plus a reproducible blind eval of “does it sound like me”. 把你的工作方式做成 AI 数字分身。
MIT -
TaskDeck for Claude Code: /taskdeck:track and the TaskDeck connector. TaskDeck (taskdeck.me) is a hosted Kanban board that people and AI assistants such as Claude, ChatGPT and Cursor share over MCP.
MIT -
hand-crafted cybersecurity tools. made by me and aa certain LLM. made to be usable by humans and AI agents through an MCP server, that comes packed with the repo.
-
IGL, Identity Governed Logic: a governed identity graph, policy engine and signed audit chain for AI agents. Every answer cites its records; every action leaves a receipt. Runtime, platform API, MCP server and the id-me.ai site.
Apache-2.0 ★ 1 -
Notify Me! for Shopify (back in stock, pre-order, wishlist) - MCP server config, CLI and Claude Code plugin for AI agents. App: apps.shopify.com/preorder-back-in-stock
npm MIT ★ 2 -
an MCP server for the services I like to use with AI agents, which you should probably fork and modify for your own use. No PRs accepted, this is just for me. Not private because you or a bot might get something out of what you see here.
Apache-2.0 ★ 3 -
Chat with your database using plain English! This is a Model Context Protocol (MCP) server that transforms natural language into SQL queries using AI. Instead of writing complex SQL, just ask questions like "Show me all users from New York" and get instant results.
★ 2 -
Voice-first restaurant MCP server (Rust, Streamable HTTP, MCP 2025-11-25): allergen-aware menu search, table negotiation and holds, pickup orders, opt-in memory with forget-me, and simulated deposits the AI can't approve. Built for the Amazon Developer Hackathon.
MIT ★ 1 -
Open-source meeting rooms with live transcription, an AI assistant that answers into the meeting, written minutes, and your own coding agent (Claude Code, opencode) in the room over MCP. Self-host on AWS or use kelabo.me. Model- and supplier-independent.
npm MIT ★ 3 -
Jake Gaylor is a software engineer (platform engineering, Kubernetes, developer tooling) whose personal site publishes an agent-native representation of his resume. ai.jakegaylor.com serves a hosted Model Context Protocol server (Streamable HTTP at /mcp, a legacy SSE transport, and the same server as the npm stdio package @jhgaylor/me-mcp) with 12…
-
Kine(/kaɪn/)· 为 AI 智能体设计的确定性视频剪辑/合成引擎:第 N 帧 = f(N)。TypeScript monorepo(8 包)+ Edge CDP 逐帧抓帧 + ffmpeg 分片编码 + Python 侧车。能力:32 个 CLI/MCP 工具,读事实→改 DSL→量结果→验证出片;声明式 timeline.yaml 单一真源;逐帧确定性渲染、字节级复现;8 类指标 + 断言集 + 基线回归;34 个 widget;15 种转场;离线 SFX;字幕;浅色模式。已出片 world.execute(me) MV(25 幕 / 121.9s)等。
MIT ★ 1 -
RASONno update data
A complete AI infrastructure for analytical modeling — not just a REST API wrapper. Provides any MCP-compatible AI assistant with access to **[RASON](https://www.solver.com/rason)** by [Frontline Systems](https://www.solver.com) for building, analyzing, and solving optimization, simulation, data science, and decision models. Includes a searchable library of nearly 200 example models, starter templates for every model type, structural model analysis, and guided workflows for solving and result interpretation. An AI assistant connected to this server can formulate a model from a business problem description, find relevant examples, explain model structure, submit it for solving, and present results in a goal-oriented way — closing the loop with suggested next steps and improvements. **Example interactions:** - "Find me a portfolio optimization example" - "Build a scheduling model for 8 employees with shift constraints, solve it, and show the schedule" - "This model is infeasible — run diagnostics and suggest which constraints to relax"
smithery -
YouTube Metadata — FlashDatano update data
# YouTube Metadata — FlashData Read YouTube video details, descriptions, statistics and available chapters. Inspect formats or prepare timestamped chapter navigation. Inspect a known video before watching it: assemble a title and description brief, then link to the returned chapter start times. [YouTube Metadata API documentation and examples](https://flashdata.dev/docs/sources/youtube_metadata?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_metadata-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Metadata listing](https://smithery.ai/servers/flashdata/youtube-metadata) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_metadata`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_metadata` without submitting a data query. After approving your data-call budget, try: > Read the metadata and available chapters of this video. Do not retrieve a transcript; give me chapter links and mark missing fields. This server exposes `youtube_metadata`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id is an 11-character YouTube ID. include_formats and include_chapters are booleans, both default true. Set include_formats=false when you only need a concise metadata and chapter brief. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_metadata", "arguments": { "video_id": "dQw4w9WgXcQ", "include_formats": false, "include_chapters": true } } ``` ## Work with the output Read results[0], including title, description and chapters when present. Pair chapter start_time/end_time with the video watch URL to prepare a navigation brief. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_metadata", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "title": "Example video", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90, "chapters": [ { "title": "Introduction", "start_time": 0, "end_time": 30 } ], "description": "Example description" } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Fields and chapters may be absent. Metadata does not include a transcript; transcript retrieval is a separate paid call. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
mes-mcp-serverstale
基于MES系统API的MCP服务
npm MIT -
MCP Server for Aibolit
npm MIT -
MCP Server for Cribl API Interaction
npm MIT -
A Salesforce connector MCP Server.
npm MIT -
MCP server for consulting powerful AI models
npm MIT -
Montenegro Official Legislation, Case Law & Citation Verification MCP Server
NOASSERTION -
MCP server for Linode API
npm MIT -
@link.me/mcpactive
Linkme platform MCP server for Claude, Cursor, and other AI agents
npm UNLICENSED -
Production-ready Discord MCP Server
npm MIT -
MCP index access to the AgentOps Public API.
npm MIT -
Integrate the Productboard API into agentic workflows via MCP
npm MIT -
一个专为开发者设计的 MCP 服务器,旨在将个人核心知识文档(简历、认知内核、项目概览)集成到 AI 辅助开发环境中。
npm MIT