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.
-
A MCP server providing offline Motion.dev documentation access and intelligent animation code generation for React, JavaScript, and Vue. Features multi-framework support, advanced search capabilities, and production-quality component generation through AI.
★ 14 -
reo-census-mcpupdated this year
Product usage HTTP client for Reo (POST JSON to ingest.reo.dev/api/product/usage)
npm MIT -
shopclaw-mcpgithub.com/h3nri-dev/shopclaw-mcpupdated this year
ShopClaw.dev — Search 364M+ Shopify products via MCP, REST API, or Agent Skill. For AI agents and marketplace integration.
MIT ★ 1 -
@veriify/mcpupdated this year
Veriify MCP server — scan any website or your localhost dev server for security, accessibility, performance, and dark patterns from inside Claude Code, Cursor, Windsurf, and other AI dev tools. One Product Health Score with evidence for every finding.
npm UNLICENSED -
mcp_serversgithub.com/sameerbudhiraja/mcp_serversupdated this year
Production-ready MCP servers for GitHub, Bitbucket, GitLab & Jira - enabling AI assistants to interact with your dev platforms
MIT ★ 2 -
mcp-commander-consolegithub.com/jacobcdsmith/mcp-commander-consoleupdated this year
Production-ready MCP server with a cinematic ops dashboard — dual-interface (stdio + HTTP), 13 dev/system tools, Docker-scale observability with Grafana & Prometheus.
npm ISC -
Pull production into dev in one command, see who is hitting your server, and publish posts — for Trellis WordPress sites. CLI, trellis-cli plugin and MCP server.
MIT ★ 2 -
localdb-mcpgithub.com/SedlarDavid/localdb-mcpupdated this year
Local MCP server so AI agents (Cursor, Claude Code, etc.) can query Postgres and SQL Server without ever seeing credentials. Dev/test only—never use with production.
go MIT -
MCP-Servergithub.com/lreb/MCP-Serverupdated this year
The local-dev MCP server is a production-ready implementation of the Model Context Protocol that provides AI assistants like Claude with tools for local development tasks. It serves as an excellent base project for anyone looking to build their own MCP server.
MIT ★ 1 -
Multi-Database MCP Server: Unified PostgreSQL database access for AI-powered IDEs. Connect to multiple databases through a single MCP server, switch between them dynamically, execute SQL queries, explore schemas, and manage connections without restarting your IDE. Perfect for developers working with dev/staging/production databases.
npm MIT -
Production-grade 22-level on-page + AI-search (RAG/LLM) SEO auditor with 14 dev-ready deliverables, CLI + MCP server — real measured data, no mocks. Node.js + Puppeteer + Express.
MIT ★ 1 -
Local mirror of AI-dev-tool changelogs (Anthropic, Cursor, Aider, Continue, MCP SDKs, etc.) with hybrid FTS5 + sqlite-vec retrieval, MCP server, curated cross-product synergies, and a fine-tuned changelog→action synthesizer (cs-actions:v1).
npm MIT -
MCP server (stdio) to manage and publish Coco Wallet mini apps from your assistant (Claude Code / Claude Desktop). Scaffolds a minimal Next.js starter, runs the dev server, opens tunnels, deploys to production and publishes to the develop catalog via the
npm MIT -
repo-mcpgithub.com/westkevin12/repo-mcpupdated this year
A professional-grade MCP server for cleaning Git repositories. Automate secret audits with TruffleHog, sanitize history using git-filter-repo, and intelligently squash noise commits to transform messy dev logs into clean, production-ready codebases.
GPL-3.0 ★ 2 -
bullhorngithub.com/mean-weasel/bullhornupdated this year
Agent-first social media scheduler that works from your IDE via MCP. Not an auto-poster or AI slop machine — a workspace for thoughtful devs and product leaders who use Claude Code, Codex, and other agentic tools to craft, iterate on, and schedule real content alongside their code. iOS app included.
AGPL-3.0 ★ 4 -
MCP server for production-grade UI and brand design — 37 tools: anti-slop quality gates, OKLCH tokens with auto dark mode, WCAG 2.1 audits, React/Vue/HTML output, CSS/SCSS generation, motion.dev & anime.js, and logo/brand-mark design with a 1,432-mark reference library.
MIT ★ 17 -
Google Shopping — FlashDatano update data
# Google Shopping — FlashData Search Google Shopping for products, merchants and price labels. Collect comparable offer snapshots with product IDs and source links. Capture a product shortlist and compare later snapshots by productId or link, keeping each merchant and its original currency-formatted price. [Google Shopping API documentation and examples](https://flashdata.dev/docs/sources/google_shopping?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=google_shopping-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the Google Shopping listing](https://smithery.ai/servers/flashdata/google-shopping) 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 `google_shopping`. 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 `google_shopping` without submitting a data query. After approving your data-call budget, try: > Find wireless headphone offers in the US and make a comparison table of product, merchant, displayed price and link. This server exposes `google_shopping`, `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 query is required. Use gl and hl for the target market; num and page control result requests. Prices remain their returned strings; normalize currencies in your own application only when you have the necessary context. 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": "google_shopping", "arguments": { "query": "wireless headphones", "gl": "us", "hl": "en", "num": 10 } } ``` ## Work with the output Read results[0].shopping. Join a stored prior snapshot by productId or link, then compare the original price strings and retain title, source and captured time. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "google_shopping", "status": "done", "results": [ { "shopping": [ { "title": "wireless headphones", "link": "https://example.com/research", "snippet": "Search fixture", "position": 1, "productId": "product-1", "price": "$49.00", "source": "Example merchant" } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Currency-formatted price labels are not normalized numeric prices. This does not calculate exchange rates or guarantee stock, checkout prices or complete market coverage. 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 -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) 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_search_extended`. 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_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `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 max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. 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_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. 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 -
mcp-dev-coregithub.com/Elorro/mcp-dev-coreupdated this year
A production-ready MCP server for safe, structured, and auditable developer workflows.
MIT -
@harpal-dev/x-mcpgithub.com/product-x/ai-test-managementupdated this year
MCP server for Product-X Test Management System - Manage test cases, modules, components, and subcomponents via Cursor and VS Code
npm MIT -
Smart timer and rhythm tracker for coding duration, ergonomic breaks, and developer productivity for Antigravity AI (Sidecar UI + MCP Tools + Pomodoro).
MIT ★ 1 -
@mnicole-dev/rize-mcp-serverupdated this year
MCP server for the Rize time tracking GraphQL API
npm MIT -
@nepvibe/dev-journal-mcpgithub.com/surazzarus/dev-journal-mcpupdated this year
A personal dev journal MCP server — log your daily work and generate standups via Claude
npm MIT -
@locus-dev/mcp-servergithub.com/jonybur-oc/locusupdated this year
User stories as structured AI coding context — scope-check via get_active_story (Claude Code, Cursor, Windsurf)
npm MIT -
Autonomous line producer for film shoots — Gemini + CP-SAT + Grafana MCP. The LLM formulates, the solver decides, a human approves.
Apache-2.0 -
Native macOS local dev-process manager — one screen for all your local dev servers: live colored logs, CPU/mem metrics, port-ready & conflict detection, LAN QR, ⌘K quick-launch, and MCP so AI tools can drive your processes.
MIT ★ 4 -
dev.agentbrush/mcp-serverno update data
On-brand image generation (product shots, app icons, OG cards, sprites) for AI coding agents.
npm -
argustest.devgithub.com/AbleVarghese/argustest.devupdated this year
iOS device monitoring + AI-assisted debugging via MCP for Claude Code & Cursor users. Public face of the private product.
-
mcp-shopify-devupdated this year
MCP server for Shopify Admin API — manage products, inventory, media, and files via Claude
npm ISC -
zentao-dev-mcpupdated this year
MCP server for Zentao project management - developer tools for tasks, bugs, stories and products
npm MIT -
Production-ready developer assistance through Model Context Protocol (MCP).
npm ISC -
okta-dev-assistantgithub.com/rangaprakash-okta/okta-dev-assistantupdated this year
MCP server for Claude Code — helps developers adapt Okta's official sample code to their production apps and SDK grounded answers
npm UNLICENSED -
Production-ready MCP server for real-time frontend development news aggregation and analysis. Built with Go, featuring enterprise-grade architecture, comprehensive testing, and Docker deployment.
MIT ★ 1 -
BrinkCommerce MCP Server - API documentation and management tools for products, orders, inventory, prices, discounts, taxes, and stores
npm MIT -
Enhanced DevOrchestrator MCP Server with Sequential Thinking Integration, Production Mode Compliance, and Project-Aware Task Execution
npm MIT -
AI-native web production platform — sitemap, content drafts and visual review unified around pages. MCP-first, Cloudflare-native (Workers+D1+R2). AGPL-3.0
AGPL-3.0 -
mcp-dev-toolsgithub.com/emmahuang-ee/mcp-dev-toolsupdated this year
A production-quality MCP server exposing three read-only local development tools: SQLite queries, TCP port checks, and Git working-tree summaries. Built on FastMCP.
MIT -
SuperBryn MCP server — run the voice-agent eval loop and read your production call logs from Claude Code, Claude Desktop, or Codex.
npm MIT -
Email sending (used by Deploya.dev)no update data
Compose and send emails directly from your LLM applications without the hassle of copying and pasting. Integrate seamlessly with Resend's API to streamline your email communication. Enhance your productivity by letting your agents handle email tasks effortlessly.
smithery -
langgraph-dev-navigatorgithub.com/botingw/langgraph-dev-navigatorupdated this year
An opinionated development framework for building production-ready AI agents with LangGraph. It grounds AI coding assistants (Cursor, Windsurf, Cline) and guides them to use local, official documentation, ensuring reliable, secure, and observable agentic workflows.
MIT ★ 23 -
Connect any AI coding tool to 1,600+ production-ready prompts and real React/Tailwind components. Open MCP server + AGENTS.md — works in Claude Code, Cursor, Windsurf, VS Code, Codex, Zed and more. ~6x cheaper than generating from scratch.
MIT ★ 3 -
Your projects, dev servers, ports, journal and weekly summary in one place: a local dashboard, a dx command, and tools your AI coding agent can use to run your app and see its errors. No setup.
npm MIT -
devassist-workspacegithub.com/akshita270/devassist-workspaceupdated this year
MCP server connecting Claude AI to your dev workspace — tasks, notes, GitHub issues & web dashboard
-
MCP server for Vlexor — AI video editing, game-asset generation, and motion-graphics production from Claude Code, Cursor, and other MCP-capable agents.
MIT -
@tymio/mcp-serverupdated this year
Tymio MCP CLI: OAuth stdio proxy to hosted MCP, API-key REST bridge, bundled PM/PO/DEV/workspace agent personas
npm -
context-syncgithub.com/Intina47/context-syncupdated this year
Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex, antigravity, etc.
npm MIT ★ 190 -
Self-hosted product analytics and App Store revenue for indie iOS apps: one Go binary with SQLite, a web dashboard, email reports and alerts, and a read-only query layer your AI agents can use through the CLI or MCP.
go MIT ★ 1 -
DonutStudio: a free, closed-source harmonic composition workstation and JI-native MIDI editor (microtonal, xenharmonic, EDO). Harmonic link chains, Scala, MTS-ESP, 16-track host, VST3/CLAP. Public dev resources: Lua scripting API, MCP server for AI agents, skills for Claude Code/Cursor/Codex.
MIT ★ 2