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.
-
@just-every/designupdated this year
MCP stdio server for design.justevery.com (Design App API)
npm MIT -
MCP server for running long-running AI tasks using @just-every/task
npm MIT -
@just-every/12uiupdated this year
Node clients for 12ui conversion and private Design Corpus retrieval, plus the conversion CLI and MCP server
npm MIT -
poke-whoop-mcpgithub.com/abhishek-sankar/poke-whoop-mcpupdated this year
Just a little smth to push me every evening when I don't hit my health goals
-
Reference MCP server that authorizes every tool call against Keycloak realm roles — per-tool RBAC, not just authenticated/unauthenticated.
MIT ★ 2 -
Every smart contract deserves intelligence, not just data. MCP server for on-chain calculated indicators (EMA, RSI, VWAP, Bollinger, volatility) via Chainlink.
pypi MIT ★ 1 -
Export your AI coding agent chats (Claude Code, Codex): just the conversation, or every tool call, file read and subagent. Markdown, HTML or JSON. Plugins, MCP server, CLI.
MIT ★ 1 -
With the grip of the anaconda, we hold onto every thought. No more, you know how many times I've told you that? Didn't I already tell you not to do that? Why did you do that again? No more of that shit, you just won.
GPL-2.0 -
Where's my hug at? Tell your AI agent what you want a model to do. It finds what Hugging Face already has for it, what to fine-tune, and what's just code, with every model checked live.
npm MIT -
Local-first code graph for C#/.NET and Angular, served to coding agents over MCP. Understands ASP.NET routing, DI and EF Core — not just syntax. Every heuristic is marked as one. No network, no telemetry.
MIT ★ 1 -
wardengithub.com/dsvxmedia/wardenupdated this year
Sandboxed, egress-controlled MCP server. Runs agent-requested shell commands inside a locked-down, ephemeral Docker container: non-root, capabilities dropped, read-only fs, resource-limited, no network by default, audit-logged before execution. Every security claim verified against a live container, not just documented.
MIT -
capcut-mcp-fullgithub.com/MadeByAdi/capcut-mcp-fullupdated this year
MCP server for CapCut (Elixir, macOS + Windows). AI agents can create CapCut projects that actually OPEN in the editor, not just list -- fixes the timeline-id/manifest-id bug that silently breaks every other write-capable CapCut tool.
★ 1 -
Tells your AI agent which parts of your idea already exist on GitHub, which to adapt, and which to just write — every repo verified live. MCP server, Claude Code plugin, and agent skill.
GPL-2.0 ★ 56 -
Where my hug at? Tell your AI agent what you want a model to do. It finds what Hugging Face, Kaggle, Zenodo, ModelScope and Roboflow already have for it, models and data alike, what to fine-tune, and what's just code, with every pick checked live.
npm MIT -
Let your coding agent see the UI it just changed, motion included: screenshots logged in at every width, and what's wrong as text (animations that snap, shrink, flicker or freeze, content that jumps after load). A shell command, an MCP server and a Claude Code plugin. Local.
MIT -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
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 Transcript — FlashDatano update data
# YouTube Transcript — FlashData Retrieve available YouTube transcript text with start and end timestamps. Build cited summaries, searchable notes and transcript exports. Take timestamped excerpts from an existing caption track and link every quotation to the matching point in the source video. [YouTube Transcript API documentation and examples](https://flashdata.dev/docs/sources/youtube_transcript?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_transcript-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Transcript listing](https://smithery.ai/servers/flashdata/youtube-transcript) 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_transcript`. 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_transcript` without submitting a data query. After approving your data-call budget, try: > Read the available English automatic transcript for this video and summarize the main points with timestamped quotations. This server exposes `youtube_transcript`, `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 required; language defaults to en. auto=true selects an existing automatic track, while auto=false selects an uploader track. Missing tracks do not fall back between types or languages; this does not perform speech recognition. 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_transcript", "arguments": { "video_id": "dQw4w9WgXcQ", "language": "en", "auto": true } } ``` ## Work with the output Read results[0].segments. Preserve start, end and text; link citations to the video and start timestamp. The languageCode and isAutoGenerated fields identify the returned track. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_transcript", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "languageCode": "en", "isAutoGenerated": true, "segments": [ { "start": 0, "end": 3, "text": "Example transcript." } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling auto=true selects existing automatically generated captions; it does not run speech recognition. Missing tracks do not fall back to uploader captions or another language. 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 -
The canonical 12ui CLI, SDK, MCP server, and visual interface design skills
npm MIT