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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
MCP server for Firecrawl Simple — a web scraping and site mapping tool enabling LLMs to access and process web content
npm MIT ★ 1 -
Free to self-host goal & process maps with an AI advisor, REST API and MCP server — for humans and AI agents. Your data never leaves your server. Open source (MIT).
npm MIT ★ 14 -
SAP-discovery-agentgithub.com/WasifAkram1997/SAP-discovery-agentupdated this year
AI-powered agent that maps business processes to SAP ERP functionalities using LangGraph, MCP Server, and GPT-4
★ 1 -
Headless MCP server for QGIS 4.x: layers, Processing algorithms and map export from Claude, no Desktop needed
NOASSERTION -
Offline flowchart editor for Windows — map sources, prerequisites and processes on one canvas. AI-agent control via CLI & MCP.
MIT -
An in-process MCP bridge into a running VOCALOID 6 - attach, scan, read and chain from inside the editor - plus the measured reason its note map is not there yet.
MIT -
Portuni is a shared map of how your organization works – its processes, projects, areas, and principles – held as one graph that every tool and every AI agent can read. People and agents draw from the same picture instead of rebuilding context from scratch in every app.
Apache-2.0 ★ 2 -
node-debugger-mcpgithub.com/jaenster/node-debugger-mcpupdated this year
MCP server that gives Claude a real Node.js debugger — breakpoints, stepping, scope inspection, eval, source-map-aware BPs, child-process and worker-thread auto-attach, AsyncLocalStorage discovery. Speaks the V8 Inspector Protocol.
npm MIT -
Self-hosted MCP server and Tavily-compatible API for AI agents: web search, extract, crawl and map in one lightweight CPU-only Python process. JS pages via headless Chromium, PDF, no API keys.
AGPL-3.0 ★ 3 -
BEA - Binary Execution Analysis: dynamic binary analysis for AI agents. MCP server + CLI for Windows x64: Frida hooks with float args, hardware watchpoints, memory scans, Ghidra address mapping, in-process oracle calls, Unicorn emulation diffs, evidence-first results.
MIT ★ 1 -
MCP server for intelligent, read-only analysis of Excel workbooks (.xlsx/.xlsm), with structured output tuned for LLM consumption. Built to map the as-is state of administrative processes that rely on multiple linked Excel files. The server runs locally and returns structured summaries instead of raw spreadsheet dumps.
MIT -
MacJetgithub.com/jeppsontaylor/MacJetupdated this year
MacJet: The flight deck for your Mac. Go beyond Activity Monitor with app-centric grouping, high-resolution thermal/energy metrics (temp, fan, energy impact), and intelligent Chrome tab-to-PID mapping. Includes a built-in MCP server, making it the first process monitor built for AI agents. Fast, terminal-native, and purpose-built for macOS.
MIT ★ 7 -
Unified memory-layer plugin for Claude Code. One MCP server, multiple typed corpora (vault, code, plans, docs, research, project-map), unified cross-corpus knowledge graph, conditional tool registration, in-process drift detection, and human↔code translat
npm MIT -
magiclane-mcp-serverno update data
The Magic Lane Model Context Protocol (MCP) Server enables any AI agent or application to become a geospatially intelligent assistant, capable of acting as a reliable companion for pedestrians, cyclists, and drivers alike. Built on top of Magic Lane's advanced mapping and routing technology, this TypeScript-based MCP server empowers AI agents to: - Understand and process geospatial data - Interpret user intent in a spatial context - Deliver accurate, contextually relevant navigation guidance By leveraging Magic Lane's global map data and real-time geospatial intelligence, the MCP Server enables deeply personalized navigation and trip-planning experiences through core tools: - Intelligent Search: find addresses, points of interest (POIs), or coordinates with intelligent search capabilities and POI category filtering. - Smart Routing: generate optimized routes between multiple waypoints with support for various transport modes, route preferences, and dynamic POI integration. - Round Trip Planning: create circular routes that start and end at the same location, perfect for jogging routes, cycling loops, or delivery runs. - Reverse Geocoding: convert geographic coordinates into detailed address information including street name, city, state, country, and postal code. - Isochrone Analysis: calculate reachability polygons showing areas accessible within specific time or distance constraints. - Route Visualization: create visual map images of calculated routes, isochrones, and round trips for immediate geographical context and presentation. - Geofence Management: create, manage, and query geographic boundaries for asset monitoring, location-based alerts, and spatial analysis with support for polygons, circles, and rectangles. - Interactive Map: Display an interactive vector tile map directly inside the conversation using MapLibre GL JS and MagicLane vector tiles. Supports location views, route visualization, isochrone overlays, round trip routes, search result markers, geofence areas, and custom coordinate paths — with one or many overlays per map and pan/zoom interactions. The map functionalities can be visualized as high-quality map images through our new beta feature to generate custom map views with markers, bounding boxes, or location-centered areas without route calculation, complementing route visualization for routes, isochrones, and round trips. Together, these capabilities enable AI agents to act as true geospatial copilots - understanding spatial context, anticipating user needs, and optimizing every journey with precision and ease.
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 -
Official Wavelength remote MCP server: turn calls, notes, and code into process flow diagrams
NOASSERTION ★ 1 -
Local-first diagrams, data and code analysis, and deterministic process simulation, with a local API and MCP.
MPL-2.0 -
Requstory CLI: map how a company works from its website, find the gaps, check ease scores and AI-agent readiness.
MIT -
MCP server for managing Next.js development processes with AI tools
npm MIT -
Free flowchart editor for the web, iPhone, iPad and Mac. Draw by hand, or let ChatGPT and Claude draw over MCP.
-
inspector-mcpgithub.com/AbianS/inspector-mcpupdated this year
MCP server for debugging live Node.js processes via Chrome DevTools Protocol
npm ★ 2 -
Prediction market velocity signals mapped to equity positions via Robinhood's agentic trading MCP
★ 2