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.
-
mealforgegithub.com/gavdevs/mealforgeupdated this year
AI-planned weekly meals, self-hosted. Plan in chat with any MCP-capable agent — get recipe cards, cook mode, and an auto-derived grocery list.
MIT ★ 2 -
open-agent-kitgithub.com/goondocks-co/open-agent-kitupdated this year
| Maintenance Mode | OAK automatically captures the plans, decisions, and trade-offs that usually vanish. Intelligence powered memories, context injection, autonomous agents, and more.
MIT ★ 10 -
Agentic MCP — local coding tools for ChatGPT Developer Mode and other MCP clients. Tested with ChatGPT Plus via HTTPS tunnel; availability varies by plan and rollout. Independent project, not affiliated with OpenAI.
npm MIT -
MCP server that lets Claude Code consult the Codex CLI for plans, second opinions and images, as durable background jobs. Optional write mode, and a live jobs pane.
npm MIT -
MCP server for Thermomix & Cookidoo: let Claude or any AI assistant create Cookidoo recipes with guided cooking (TM6/TM7 modes, Varoma, Turbo), search the recipe catalogue, plan your week and fill your shopping list.
MIT -
Gives VS Code agent mode planning superpowers with dynamic todo lists
MIT ★ 39 -
Map-first trip planning for Claude, ChatGPT and any MCP client. 37 tools: itineraries, routed transport across 11 modes, trip review, sharing.
MIT -
Local, offline MCP server for jevify: find the AI calls in your code that are really decisions, then plan their migration to JEV in shadow mode.
npm Apache-2.0 -
Delegate multi-file coding work from Claude Code, Codex, Copilot, or any MCP client to Cursor's CLI agent — structured results, plan mode, and changed files.
npm MIT -
Zero-token ($0) E2E Playwright QA engine for Claude Code, Google Antigravity & Cursor. Crawls live DOMs into ~1.2k-token accessibility maps, runs self-healing intent plans locally, and compiles to native .spec.ts. Dual-mode: Agent Skill CLI + Stdio MCP Server.
MIT ★ 2 -
Open-source AI coding workbench in Rust: desktop app (GUI) + terminal TUI. Multi-session agents, plan and goal modes, built-in terminal and browser, diff review and Git commits, MCP client and server, skills, knowledge base and long-term memory. Works with OpenAI, Anthropic, Gemini, DeepSeek and more.
MIT ★ 21 -
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 Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) 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_trainability`. 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_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `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 Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. 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_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. 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 Download to Cloud Storage — FlashDatano update data
# YouTube Download to Cloud Storage — FlashData Deliver YouTube video, audio or clips to your own S3 or other supported cloud storage. Track asynchronous delivery and its output manifest. Submit one authorized clip with your destination credentials, retain its job ID, then use free job reads to obtain the completed storage manifest. [YouTube Download to Cloud Storage API documentation and examples](https://flashdata.dev/docs/sources/youtube_download?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_download-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Download to Cloud Storage listing](https://smithery.ai/servers/flashdata/youtube-download) 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_download`. 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 per-TB rate. Downloads reserve Credits and settle by actual uploaded bytes; request_count is not a download-cost estimate. 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_download` without submitting a data query. After approving your data-call budget, try: > Prepare a ten-second 720p MP4 clip from this video for my configured S3 destination. Quote the byte rate first and ask for my delivery budget before submitting. This server exposes `youtube_download`, `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 and storage are required. Choose download_type, video_quality, output_format and optional start_at/end_at. Only async is supported. Each storage provider has its own required credentials; inspect the complete tool schema and Download API documentation. 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_download", "arguments": { "video_id": "jNQXAC9IVRw", "mode": "async", "download_type": "audio_video", "video_quality": "<=720", "output_format": "mp4", "start_at": "00:00:00", "end_at": "00:00:10", "storage": { "storage_type": "s3", "storage_url": "your-media-bucket", "access_key": "YOUR_ACCESS_KEY", "secret_key": "YOUR_SECRET_KEY", "region": "us-east-1", "object_prefix": "flashdata-clips" } } } ``` ## Work with the output Submit once, save the returned id, and call get_job with job_id until job.status is completed. Read output.results[0] for file_url, file_size, downloaded_bytes and output_format. Pending or processing is not completed delivery. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "job": { "id": "job_EXAMPLE", "source": "youtube_download", "status": "completed" }, "output": { "results": [ { "file_url": "s3://customer-bucket/clip.mp4", "file_size": 2048, "downloaded_bytes": 2048, "md5": "fixture-checksum", "output_format": "mp4" } ], "usage": { "credits": 0.001 } }, "http_status": 200, "request_id": "fixture-request" } ``` For example, after receiving the real id, call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Poll only the read, not the original download submission. Storage credentials travel to FlashData to perform the upload and may be retained by your MCP client in tool history; use narrowly scoped credentials and your client's protected configuration. ## Limits and result handling Only asynchronous delivery is supported. Supply your own destination and credentials; media access and retention follow your storage settings. Private object URLs are not public download links. Charges reserve Credits and settle by uploaded bytes. 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 -
Catch the bad plan before you spend the tokens. Cross-LLM peer review via MCP.
MIT ★ 2 -
inspectrumgithub.com/yannmenec/inspectrumupdated this year
Automatic Codex plan review in Claude Code; on-demand in local MCP hosts; human approval stays yours
npm MIT -
Manage Coolify from AI agents. A local MCP server with API discovery, composed workflows, and dry-run request plans.
MIT -
Manage Coolify from AI agents through a local MCP server with API discovery, composed workflows, and dry-run request plans.
npm MIT