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.
-
PBPgithub.com/MadGapun/PBPactive
Local AI job application assistant for the German-speaking job market (DACH) — job search, application tracking, CV analysis. MCP server for Claude Desktop, self-hosted, no cloud. Deutsch: dein Bewerbungs-Helfer, läuft komplett lokal.
MIT ★ 7 -
applycairn-releasesgithub.com/scumunna/applycairn-releasesupdated this year
Local-first AI job search assistant for Codex and Claude Desktop: tailored resumes, job scoring, application tracking, outreach, and interview prep.
NOASSERTION -
Go CLI and MCP server for managing Parallels Desktop VMs on macOS and inspecting, controlling, and screenshot-testing Windows applications.
GPL-3.0 -
Native desktop-control MCP server for AI agents. Automate Windows, macOS, and Linux applications through accessibility APIs, with background actions, app allowlisting, and stdio or authenticated loopback HTTP transports. Copy description
MIT -
Closed-loop, state-verified Windows automation runtime for AI agents — from EDA and CAD to any desktop application.
MIT -
A Spring Boot application that implements the Model Context Protocol (MCP) server, providing AI-powered tools for different platforms. This server can be integrated with Claude Desktop and other MCP-compatible clients.
MIT -
IANA-registered format (application/vnd.faf+yaml) • Persistent project context • MCP server for Claude Desktop • MIT License
npm MIT -
MCP server that connects Claude Desktop for Windows to the Windows Calculator application, enabling Claude to perform accurate mathematical calculations using Windows' native calculation engine. Automatically starts with Claude Desktop and provides seamless integration for precise arithmetic operations.
NOASSERTION ★ 1 -
Universal MCP server written in Rust, with a Hub that exposes only two tools: a language model drives desktop applications by running scripts in them.
MIT -
🧞♂️ AI-powered Model Context Protocol (MCP) server for autonomous desktop control, intelligent job application form filling, local application tracking, and AI mock interview preparation.
MIT ★ 1 -
argo-cd-mcp-servergithub.com/kamolc4/argo-cd-mcp-serverupdated this year
Production-ready Argo CD MCP Server template for the Model Context Protocol (MCP). Build AI integrations with Argo CD using TypeScript, API token authentication, applications, sync, health, deployments, Claude Desktop, Cursor, Windsurf, and other MCP clients.
MIT -
Model Context Protocol (MCP) server for reusable checklists and dated runs of them: pass, fail, not applicable, and a sign-off. Checklists you build once and run many times, and the dated record of each run that somebody signs. Works with Claude Desktop, Claude Code and Cursor.
MIT -
MCP drawing application with TypeScript server and React frontend for real-time canvas visualization through Claude Desktop.
MIT ★ 4 -
This is a MCP application demo that enables Claude Desktop to create, read, and manage persistent sticky notes.
-
An MCP (Model Context Protocol) server providing a tool to interact with the ChatGPT macOS desktop application.
npm MIT -
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 -
Local MCP tools for AI agents to debug Firefox and control Windows applications. Codex desktop plugin and VS Code support.
MIT -
AWS SES Email Senderno update data
Send emails directly from your applications using AWS SES. Integrate seamlessly with Cursor or Claude Desktop to compose and dispatch emails without manual copy-pasting. Enjoy features like CC, BCC, and customizable sender addresses for enhanced email management.
smithery -
Desearch AIno update data
Enable real-time AI-powered search capabilities including Twitter (X) and web search directly within your LLM applications. Access relevant links and summaries instantly to enhance your AI workflows. Integrate seamlessly with Claude Desktop and Cursor IDE for enriched search experiences.
smithery -
A MCP server that bridges AI agents to the macOS desktop: the accessibility tree, synthetic mouse and keyboard input, screenshots, window and application control, the shell, preferences, launchd, processes, the filesystem and web scraping.
MIT -
🌙 Traditional Chinese Lunar Calendar MCP Server - 18 tools for auspicious date checking, festival information, moon phases, and zodiac insights. Ready for Claude Desktop and AI applications.
MIT ★ 2 -
Deep Dive MCP Serverno update data
Provide a customizable MCP server implementation that integrates with Claude Desktop and other clients. Enable dynamic loading and execution of tools and resources via the Model Context Protocol to enhance LLM applications. Simplify installation and deployment with support for Smithery and containerized environments.
smithery -
A Model Context Protocol (MCP) server for accessing Central Bank of Nigeria (CBN) data and circulars. Connect this server to Cursor, Claude Desktop, or any MCP-compatible application to access CBN regulatory information directly in your AI conversations. 🚀
★ 19 -
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
npm NOASSERTION ★ 1,276 -
Balldontlie Sports Data Serverno update data
Provide up-to-date information about players, teams, and games for the NBA, NFL, and MLB. Query detailed sports data dynamically to enhance your applications or agents with real-time sports insights. Easily integrate with popular clients like Claude Desktop and LibreChat using your Balldontlie API key.
smithery -
A Windows UI Automation MCP Server for WPF, WinUI, Avalonia & WinForms UIInspect.MCP is a MCP server that gives AI agents and developer tools semantic access to Windows desktop applications. Instead of brittle pixel‑based automation, UIInspect.MCP exposes a rich, structured view of the UI
MIT ★ 4 -
@muhammadmehdi/ollama-mcp-servergithub.com/m-mehdi14/ollama-mcp-serverupdated this year
Universal MCP server for Ollama - Works with ANY IDE or application that supports Model Context Protocol (MCP). Compatible with Cursor IDE, Claude Desktop, Cline, and all MCP-compatible clients. Provides tools to list models, chat, generate text, and mana
npm MIT -
A MCP server that bridges AI agents to the Windows desktop. UI Automation, synthetic mouse/keyboard input, screenshots, window and application control, PowerShell, the registry, processes, the filesystem, and web scraping. No computer-vision model is required: the agent perceives the UI through the Windows accessibility tree.
MIT ★ 17 -
agent-portalgithub.com/Magnexis/agent-portalupdated this year
Agent Portal is a desktop-native operating environment for AI agents. Instead of limiting an LLM to code generation, Agent Portal gives it a controlled visual workspace where it can understand, navigate, test, and interact with real user interfaces, local applications, browser sessions, development environments, and project ecosystems.
NOASSERTION -
RepoTunnel is a secure local AI workspace bridge that connects ChatGPT Web and MCP-compatible AI clients to approved local projects, files, terminals, Git, GitHub, browsers, editors, and desktop applications—so AI can inspect, edit, test, run, and manage real development work without constant copy-pasting.
MIT ★ 8 -
A Model Context Protocol (MCP) server that gives AI assistants (Claude Code, Claude Desktop, and any MCP-compatible client) direct, natural language access to semantic 3D city models in CityGML managed within a 3DCityDB V5. Also includes an agentic Chatbot application using the MCP server with commercial or locally running LLMs.
Apache-2.0 ★ 21 -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
MCP server for the AI Patent Search Generator — patent dossiers, prosecution history, Office Action AI analysis, citation/family/CPC lookups, and Google Patents search. Works in Claude Code, Claude Desktop, Cursor, ChatGPT-with-MCP, and any other MCP-compatible client. ## Tools (11) - **dossier** — full patent intelligence: bibliographic, claims, citations, family, classifications, examiner stats. 3 credits fresh; free on 24h cache hit. - **prosecution** — USPTO file-wrapper documents (Office Actions, responses, amendments). Free. - **oa_analyze** — AI analysis of USPTO Office Actions (rejection grounds, cited prior art, suggested response arguments). First 5/application free; 1 credit each thereafter. - **search** — multi-strategy patent search against Google Patents (telescoping / onion-ring / faceted). 1 credit. - **query** — Boolean query generator (manual paste into Google Patents). 1 credit. - **similar** — Google Patents similar-documents ranking. Free. - **citations** — backward + forward citation graph, examiner-cited flagged. Free. - **family** — patent family (continuations, divisionals, foreign counterparts). Free. - **examiner** — name, art unit, allowance rate, average pendency. Free. - **cpc** — CPC classification code lookup. Free. - **balance** — credit + subscription status. Free. Requires an API key minted from the AI Patent Search Generator Chrome extension's Admin tab.
smithery -
Cardano MCPno update data
<p align="center"> <img src="https://cdn.simpleicons.org/cardano/0033AD" width="80" /> </p> <h1 align="center">Cardano MCP Server</h1> A **Model Context Protocol (MCP) server** for interacting with the Cardano blockchain from AI agents and automation systems. This server exposes wallet-aware tools for: - Submitting transactions - Fetching addresses - Reading UTxOs - Fetching balances - Resolving ADAHandles - Checking stake delegation ## Secrets 1. Copy the `.env.example` file to a new file `.env` 2. Specify your seed-phrase (`SEED_PHRASE`). Your seed-phrase is NEVER exposed to LLMs, and is only used for local wallet connection. 3. Configure the wallet connection details. Specify a Blockfrost Project ID (https://blockfrost.io/), or a Kupo & Ogmios URL. ## Docker Installation Build the container ```bash docker build -t cardano-mcp . ``` Run with your secrets ```bash docker run -p 8000:8000 \ -e PORT=8000 \ -e SEED_PHRASE="lizard,llama,frog..." \ -e BLOCKFROST_PROJECT_ID="your_blockfrost_key" \ cardano-mcp ``` ## Manual Installation Clone this repository ```bash git clone https://github.com/IndigoProtocol/cardano-mcp.git ``` Install dependencies ```bash cd cardano-mcp npm install ``` Build & Run ```bash npm run dev - or - npm run build npm run start ``` ## Connecting The URL for the Cardano MCP server will be hosted at http://localhost:8000/mcp ### Claude Desktop Configuration Add to `~/Library/Application Support/Claude/claude_desktop_config.json`: ```json { "mcpServers": { "cardano": { "command": "node", "args": ["/path/to/cardano-mcp/dist/index.js"], "env": { "SEED_PHRASE": "lizard,llama,frog..." "BLOCKFROST_PROJECT_ID": "mainnet123..." } } } } ``` ## Disclaimer By using this Cardano MCP Server and all related tools and technology (“MPC”), you acknowledge and agree that (i) your use of decentralized finance, including MPC and/or AI agents that you empower to manage your digital assets, involves various significant financial risks, including but not limited to, the risk of financial loss caused by MPC design or instructions, impermanent loss, and changes in digital asset prices; and (ii) that you are solely responsible for all MPC actions and transactions, and for securing your seed phrase, private keys, and environment configuration.
smithery -
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 -
QECTOR Decoder Workbench 1.0.7 for Windows: 19 decoders, 10 code families and an 85-tool MCP server, with versioned schemas and immutable result manifests. Portable exe and onedir builds.
NOASSERTION ★ 1 -
Free AI job applications that run on your computer: an MCP agent and local dashboard for Claude, Cursor, VS Code and Windsurf.
MIT ★ 4 -
Personal productivity desktop app for Windows — notes, tasks, projects, deliverables and calendar in one place, stored locally in SQLite. Built with Python and PySide6.
MIT -
bear-notes-mcpgithub.com/vasylenko/bear-notes-mcpupdated this year
MCP Server for Bear note taking app available as Claude Desktop extension or standalone server for any other AI tool
Apache-2.0 ★ 206 -
PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.
Apache-2.0 ★ 99 -
A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants.
MIT ★ 64 -
Android log viewer & logcat analyzer for Windows, macOS and Linux — crashes, ANRs, adb bugreports, DLT.
NOASSERTION ★ 5 -
This project is a Google Calendar MCP Server built in Python. It acts as a secure bridge between an MCP client (like Claude Desktop) and your Google Calendar, exposing full CRUD (Create, Read, Update, Delete) operations as tools for the AI to use.
-
A comprehensive MCP-based todo management system, that serves as a central nervous system for Madness Interactive, a multi-project task coordination workshop.
★ 10 -
Model Context Protocol (MCP) server for resume and cover letter writing, CV documents in Word format. Resumes and cover letters as Word files from one profile, never invented. Works with Claude Desktop, Claude Code and Cursor.
MIT -
Shared remote FluentCRM, FluentCommunity and Fluent Forms MCP/CLI with isolated site profiles, approved native tasks and private snapshots.
NOASSERTION -
🧠 Manage AI context seamlessly with the MCP server for storing and retrieving semantic memory across sessions. Enhance your AI's knowledge retention.
MIT ★ 1 -
MCP Server for Spinnaker — manage applications, pipelines, and deployments via the Model Context Protocol
GPL-3.0 ★ 5 -
An notetaking application that I use for my day to day notetaking. Made for MacOS and Windows 11.
MIT ★ 2 -
MCP server and client running on java17 for AI control of an application written in Java Swing
MIT -
Local MCP server for computer use that leaves your desktop alone: accessibility-first control, live browser handoff, an isolated Linux display, and human takeover.
MIT ★ 2 -
Devaulty is a local-first application designed to help software developers organize projects, store sensitive credentials, track ongoing issues, and manage code snippets, all in one place. Built with Go, React & Tauri v2.
NOASSERTION ★ 4 -
A desktop search engine for everything you write, read, and keep. Connect your Obsidian vault, projects, Calibre library, and code repos, then find anything with local hybrid search and expose through MCP.
Apache-2.0 ★ 12 -
Production-oriented Model Context Protocol (MCP) server for Express.js applications that enables AI clients to investigate backend systems through structured engineering tools. Exposes Git history, Winston logs, OpenAPI contracts, and source code via a secure provider-based architecture.
★ 2 -
The PokeAPI MCP Server acts as a bridge, allowing AI assistants to fetch and utilize comprehensive Pokémon data directly from the PokeAPI. This facilitates the development of intelligent applications that require accurate and up-to-date information about Pokémon, moves, items, game mechanics, and more.
★ 2