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.
-
Local thermal label editor for people and agents, with a web editor and MCP tools.
MIT -
Experimental: MCP interceptor server (SEP-2624 draft) that labels tool results and checks tool calls with ADTL trust labels
npm Apache-2.0 -
@jdickey1/mcp-google-contactsgithub.com/jdickey1/claude-skills-privateupdated this year
Google Contacts MCP server. Six tools (search, get, list labels, apply label, remove label, additive update). Grants OAuth scopes contacts.readonly + contacts.other.readonly + contacts (full write); the write surface is tool-limited to label CRUD and sele
npm MIT -
Zero-dependency MCP stdio bridge for Bridge Watch (104,209 on-chain address labels, 7 x402-metered tools)
npm MIT ★ 1 -
Source-available, white-label AI agent platform for agencies. WhatsApp, web chat, client portals, RAG and MCP tools. Self-host or explore Voysse Cloud.
NOASSERTION ★ 3 -
LabelInn MCP Server — Let AI assistants print labels, manage printers, and control your fleet. 120+ tools for Claude, GPT, and Copilot.
npm MIT -
Todoist tasks, projects, labels and sections as MCP tools.
npm MIT -
vikunja-mcpgithub.com/jrejaud/vikunja-mcpupdated this year
MCP server for Vikunja - 16 tools for projects, tasks, and labels
MIT ★ 8 -
Gmail messages, threads, labels, drafts and sending, as MCP tools via the Gmail API.
npm MIT -
gmail-mcpgithub.com/Dooc-Nuken/gmail-mcpupdated this year
MCP server for Gmail — 19 tools: search, read, send, reply, forward, draft, labels, filters, attachments
-
MCP server exposing FDA drug-safety data (labels, FAERS adverse events, recalls, label-documented interactions) with structured outputs, plus a LangGraph agent that discovers and uses its tools. Works with Claude Desktop, Cursor and any MCP client.
MIT -
gmail-mcpgithub.com/bradmccloskey/gmail-mcpupdated this year
Gmail MCP server for Claude: read, search, label. No send tool by design.
MIT -
MCP server that exposes Gitea issues, labels, milestones, and comments as tools for AI assistants
npm MIT -
MCP server exposing openFDA drug labels and FAERS adverse event reports as tools for Claude.
-
donetick-mcpgithub.com/danielrosehill/donetick-mcpupdated this year
MCP server for Donetick chores management — 27 tools for chore CRUD, labels, subtasks, timers, and more
pypi MIT -
Gmail MCP Server — read, send, search and manage Gmail through Claude using Google's official API and OAuth 2.0. 19 tools for emails, drafts, labels, threads, and attachments.
npm MIT -
google-drive-mcp-servergithub.com/us-all/google-drive-mcp-serverupdated this year
Google Drive MCP server — 96 tools for Drive, Docs, Sheets, Slides with Google Workspace awareness (Shared Drives, Labels, Approvals, domain-wide delegation).
npm MIT ★ 1 -
chain-mcpgithub.com/Dimitres-Kisimov/chain-mcpupdated this year
MCP server exposing my real analytics and optimization engines as tools for Claude: forecasting, slotting, packing, routing, leakage analysis, portfolio audit. Honest data labels on every tool.
NOASSERTION -
MCP server for Google Workspace — 53 tools for Drive, Docs, Sheets, Slides, Gmail. JSON policy engine, label-scoped access, lazy discovery. Rust.
Apache-2.0 ★ 1 -
Semantic browser automation MCP server — 24 tools for AI agents, label-based resolution, structured extraction, CDP access
MIT ★ 1 -
Agentic-Soccer-Match-Prediction-MCPgithub.com/joses2017smjh/Agentic-Soccer-Match-Prediction-MCPactive
Soccer forecasting and agent evaluation with FastAPI, LangGraph, MCP tools, historical backtests, and a labelled synthetic demo.
-
kan-mcpgithub.com/michaelruelas/kan-mcpupdated this year
MCP server for Kan.bn API - exposes 40 tools for workspace, board, list, card, label, checklist, and comment management
npm MIT -
kanbn-mcpgithub.com/panda1w56/kan-mcpupdated this year
MCP server for Kan.bn API - exposes 44 tools for workspace, board, list, card, label, checklist, and comment management
npm MIT -
a-share-mcpgithub.com/Kinneyzhang/a-share-mcpupdated this year
Source-labeled, agent-friendly Chinese A-share data tools exposed as a local MCP server.
MIT ★ 3 -
@medigamiofficial/mcpgithub.com/maximusrufus/medigami-publicupdated this year
Medigami MCP server — outcome-labeled healthcare claim intelligence as Model Context Protocol tools. Free, PHI-free, discoverable.
npm LicenseRef-Medigami-Community-1.0 -
medbridge-mcpgithub.com/MYASHWANTHREDDY/medbridge-mcpupdated this year
MCP server exposing clinical trials, FDA drug recalls, adverse events, labels, and drug-name normalization as typed, validated tools
MIT -
Authenticated, self-hosted WhatsApp MCP server that serves 96 tools for the token cost of 29, with a labeled eval for tool-retrieval accuracy. Go bridge + Python FastMCP.
MIT ★ 9 -
Read-only MCP servers for memv2 and Javis memory, for chat Bots: one combined tool with cross-check labels, plus the two single-store servers.
npm MIT -
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 -
mcp-musicbrainzgithub.com/zas/mcp-musicbrainzupdated this year
An MCP (Model Context Protocol) server that provides tools for querying the MusicBrainz music database. Search for artists, albums, recordings, labels, and more — directly from your AI assistant.
GPL-3.0 ★ 13 -
@prompt-anonymizer/mcpgithub.com/akazah/prompt-anonymizerupdated this year
A buddy check for PII before it reaches an LLM - consistent, reversible labels. MCP server (anonymize / deanonymize / scan tools) built on @prompt-anonymizer/core.
npm MIT -
GitHub CLI tools for AI coding agents, served over MCP. A read server and an opt-in write server for PRs, issues, CI runs, jobs, commits, search, labels, projects, releases, and repo files, plus hooks that redirect raw gh bash calls to the tools. Packaged for Claude Code, Codex, and pi.
npm MIT ★ 1 -
@recensus/mcpactive
Arc as MCP tools for Claude, Cursor and any other MCP client. Every write is labelled, simulated, and bounded by a daily spend limit.
npm MIT -
Free SEO tool — open-source, self-hosted alternative to Ahrefs, Semrush & Moz. 99 tools: site audits, rank tracking, keyword research, AI search visibility (ChatGPT, Perplexity, Gemini, AI Overviews), content briefs, backlinks, local SEO, white-label reports, and an agent that applies fixes. No paid APIs required. MIT.
MIT ★ 129 -
A confined generation tool: runs an LLM over a local directory read-only and emits the output as a product that is always labeled untrusted. CLI + stdio MCP server on the myelin substrate, optional in-process creatine engine. Part of the Nootropics stack.
GPL-2.0 -
mcp-uazapigithub.com/bernardoramos123/mcp-uazapiupdated this year
MCP Server for uazapi WhatsApp API — 45 tools covering instances, messages (text, media, location, contact), message actions, groups, chats, contacts, labels, bulk campaigns and AI chatbot agents. Real endpoints extracted from the official n8n node source.
★ 1 -
trello-mcpgithub.com/mab-go/trello-mcpupdated this year
An MCP server for Trello. Exposes 21 tools that let any MCP-compatible AI client manage boards, lists, cards, labels, and checklists via the Trello API.
go MIT -
Daily AI releases, tools and techniques for coding agents, each labeled with how it was checked, with public source trust scores.
NOASSERTION -
An MCP server that holds more than one Gmail account at once. Every tool names its mailbox, and each label is verified against Google before its token is used.
MIT -
Exposes MCP tools that prove every method, field, label and form pattern against your real metadata before the AI writes code.
npm MIT ★ 171 -
MCP server for Slack: several workspaces in one server, posts as you with no app label, and tools for editing, scheduling, files, canvases, Lists and more. Fork of korotovsky/slack-mcp-server.
npm MIT -
Per-brand MCP server for PayAlly — exposes product discovery, cart, and PayPal checkout as MCP tools inside any AI assistant. 100% white-labeled via env vars.
MIT -
HISTOR — public transparency log of MCP tool definitions: reads what remote MCP endpoints in the official registry advertise (never calls a tool), signs it as MTL/1 labels, appends them to an RFC 9162 Merkle log, and answers /check: is what a client received what was observed? Never calls a server safe.
pypi MIT -
MCP server for Google Search Console: 17 read-only tools covering performance queries, quick wins, CTR gaps, cannibalisation, traffic-drop diagnosis and indexing, plus a self-contained white-label HTML SEO audit in English or Italian. Claude Code plugin, .mcpb bundle, Docker.
pypi MIT ★ 10 -
gmail-mcpgithub.com/mondalraj/gmail-mcpupdated this year
An MCP (Model Context Protocol) server that provides read-only access to your Gmail account. It exposes email subjects, senders, labels, categories, and full email content to LLM-powered tools like VS Code Copilot and Claude Desktop.
-
plane-mcp-servergithub.com/philipvanlewis/plane-mcp-serverupdated this year
Comprehensive MCP server for Plane CE — 51 tools for pages, assets, work items, modules, cycles, states, labels, members, and instance customization. Rich markdown editing, image uploads, client-side filtering.
MIT ★ 1 -
Trello MCP Serverno update data
Enable AI assistants and automation tools to seamlessly manage your Trello boards, lists, cards, and labels through a standardized interface. Simplify Trello workflow management by integrating with any MCP-compatible client. Streamline project and task management with easy commands for creating, moving, and commenting on Trello items.
smithery -
Cinema 4D MCP — production fork (93 tools, +68 over upstream). Comprehensive Scene Nodes authoring/dissection (22 patterns, 802 templates, 40 verified labels), Octane OSL injection, fields, deformers, volume builders, scene snapshot/diff, recipe-based regression tests. C4D 2026 compatible.
MIT ★ 20 -
Governed AI agent over FDA labels, ClinicalTrials.gov and Medicare: MCP tools, Agent Skills, verbatim-citation grader; 95% vs 20% baseline, replicated on Claude Code and the Anthropic API
MIT ★ 1 -
@test-lab-ai/mcpactive
Model Context Protocol (MCP) server for test-lab.ai: the same operations as the testlab CLI (plans, projects, credentials, labels, data fixtures, scripts, import, and test runs) as MCP tools, with the same auth.
npm MIT -
ff-mcp-jiragithub.com/alexwolfgoncharov/ff-mcp-jiraupdated this year
Reliable Jira MCP server (Server/DC & Atlassian Cloud). 37 tools — issues, labels, transitions, comments, worklog, links, remote links, watchers, attachments, user/assignable search, field & create metadata, agile boards/sprints; body-in-error reporting,
npm MIT -
Not a demo — a published MCP server in the official registry. pip install guardrails-mcp. Tracks prompt regressions across labeled cases and hands a human the evidence to decide. No API key for the demo tools.
pypi MIT -
MCP server for the FreqBlog Music API — 25 tools covering audio features, plain-language search by description, seedless discovery by tempo/key/genre/year, similar-sounding tracks from several seeds, honestly-labelled tags, recommendations (Spotify /recom
npm MIT -
Zendriver-MCPgithub.com/ShubhamChoulkar/Zendriver-MCPupdated this year
Undetectable browser automation MCP server for LLM agents. Uses Chrome DevTools Protocol to bypass bot detection (Cloudflare, Akamai). Features token-optimized DOM walking (96% reduction vs raw HTML), smart label inference, region detection, CDP network logging, and 35+ tools for building AI agents that interact with the real web.
★ 6 -
Machship MCPno update data
# Machship MCP Server Connect your AI assistant to the Machship freight platform and manage shipping operations directly through natural language. Machship MCP enables AI agents to interact with freight workflows including consignments, quotes, carriers, labels, manifests, locations, and business entities. ## What you can do - 📦 **Consignments** — create, update, search, track, and manage shipments throughout their lifecycle - 💰 **Quotes** — retrieve carrier pricing, compare services, and evaluate transit options - 🏷️ **Labels & Manifests** — generate shipping labels, create manifests, and manage carrier bookings - 🚚 **Carriers & Services** — discover available carriers, routes, and delivery options - 📍 **Locations** — search, validate, and manage pickup and delivery addresses - 🏢 **Companies & Identities** — manage organisations, users, and account relationships - 📎 **Additional workflows** — handle attachments, invoices, custom schemas, and shipment consolidation ## Coverage **125 tools across 21 modules** providing broad access to the Machship API through a single MCP server. ## Compatible clients Works with any MCP-compatible client, including: Claude Desktop · Cursor · VS Code · Windsurf · Goose · Warp · LM Studio ## About Built by [Devkind](https://devkind.com.au) — delivering modern software solutions and AI-powered integrations for businesses worldwide.
smithery -
Six Model Context Protocol servers over curated biomedical data — ClinicalTrials.gov, openFDA (labels/events/recalls/approvals) and PubMed — pairing a pgvector hybrid-search document store with a gated relational staging layer, cited LLM tools, cross-source SQL joins, incremental refresh and usage metering.
MIT -
MCP (Model Context Protocol) server for Atlassian on-premise installations (Confluence, Jira, Bitbucket Server). Provides AI assistants (GitHub Copilot, Claude, etc.) with 60+ tools for full CRUD operations: search, create, update, delete pages/issues/PRs, manage branches, comments, labels, worklogs, transitions, and more. Supports PAT and Basic authentication.
nuget -
MCP (Model Context Protocol) server for Atlassian on-premise installations (Confluence, Jira, Bitbucket Server). Provides AI assistants (GitHub Copilot, Claude, etc.) with 60+ tools for full CRUD operations: search, create, update, delete pages/issues/PRs, manage branches, comments, labels, worklogs, transitions, and more. Supports PAT and Basic authentication.
nuget -
Desktop market-analysis workbench you drive by talking to an AI agent. A local Python sidecar does the work - indicators, candlestick and chart patterns, walk-forward backtests, volatility/regime forecasts, DeFi P&L - as 59 MCP tools; an Electron viewer draws it live. Read-only research and labeled advice: no broker, no orders.
MIT ★ 2 -
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