도구

Tableau's official MCP: lets agents query published data sources, search workbooks and views and fetch view images. Use the hosted server for Tableau Cloud with OAuth, or run locally with a personal access token for Tableau Server or Cloud.

Lets agents read delivery data and change history for Facebook and Instagram ad accounts, campaigns, ad sets and creatives to analyze performance and spot underperforming ads; read-only. Needs a Meta access token (the GoMarble installer can generate one); runs from source with Python.

Mapbox's official MCP: geocoding, POI search, driving, walking and cycling directions, travel-time matrices, multi-stop route optimization, isochrones and map rendering, plus offline distance and area calculations. Needs a Mapbox access token; an official hosted endpoint is available.

Apache Doris's official MCP: gives agents read-only access to explore table metadata, run and explain SQL, diagnose slow queries, and check cluster status, load jobs and data governance info. Needs Python 3.12+ and Doris 2.0 or later.

Official MCP for Plane, the open-source project management tool: lets agents read and manage projects, work items, cycles, modules and releases, with PQL queries. Use the hosted server with OAuth, or run locally via uvx with an API key; works with self-hosted Plane.

Leads a visible, verified code walkthrough in Neovim: confirms real behavior by running code, then authors one immutable Navi tour with short notes the viewer steps through, optionally recorded with OBS. Requires Terminal Control (termctrl), Neovim 0.10+ and navi.nvim.

Opinionated guide to production TypeScript with Effect v4: Effect.gen workflows, Context.Service and Layer services, Schema models and typed errors, Config, Schedule retries, Cache, Stream, HttpClient and deterministic tests, plus patterns to avoid. Requires Effect v4.

Railway's official plugin, bundling the use-railway skill and hosted Railway MCP so agents can create projects, deploy services, set environment variables and databases, and check logs and metrics to debug deployments. Needs a Railway account.

Has the agent use the @sveltejs/mcp CLI via npx whenever it creates, edits or analyzes Svelte components or modules: list and fetch Svelte 5 and SvelteKit docs sections, and run svelte-autofixer to catch issues and validate every component before finishing. Official Svelte skill.

Vercel's official plugin: a knowledge graph of the Vercel ecosystem, dozens of skills, expert subagents for deployment and performance, and commands for deploys, env vars and project status, covering Next.js, the AI SDK, storage and CI/CD. Needs Node.js 18+ and Bun; telemetry is opt-out.

Postman's official MCP server: lets agents manage workspaces, collections, environments and API specs, help with API testing and generate client code from API definitions. The remote version uses OAuth; the local version needs a Postman API key.

Query and manage Microsoft 365 and Azure tenants in natural language via Microsoft Graph: create users and security groups, check devices and Conditional Access policies and view cloud costs. Needs a work account with the right permissions; changes apply immediately.

Grafana Labs' official skills: dashboards and alerting, PromQL, Loki, Tempo, Mimir and Pyroscope queries, Prometheus cardinality troubleshooting, Grafana Cloud management and cost optimization, k6 load testing and plugin development. Some skills need Grafana Cloud.

Lets agents create, update and resolve incidents in ServiceNow, manage the service catalog, change requests and knowledge articles, and load only the tools each role needs. Needs a ServiceNow account and Python 3.11+ (from source); community-maintained, last updated Oct 2025.

Alibaba Cloud's official agent skills: ECS diagnosis and DR, RDS/PolarDB database checks, PAI training and EAS deployment, ACK clusters, RAM permissions, OSS and network troubleshooting, and Model Studio. Needs an AccessKey or aliyun CLI credentials.

Puts Claude in your incident channel: builds triage runbooks from past incidents, investigates alerts read-only and gives an evidence-backed first diagnosis while humans decide fixes, plus handoffs and status reports. Anthropic reference code, no longer maintained; needs Claude Team or Enterprise.

Model by conversation in open-source FreeCAD: create primitives and sketches, extrude and chamfer, run Booleans, export STEP/STL, and write and debug macros. Install and start the Robust MCP Bridge workbench from the FreeCAD Addon Manager, then pip-install the server (Python 3.11).

Firecrawl's official plugin: brings the Firecrawl CLI in as skills so Claude Code can search the web, scrape pages to Markdown, map site links or crawl whole sites. Install firecrawl-cli and set an API key first; self-hosting supported.

i18next's official CLI: finds hard-coded strings in JS/TS code, extracts translation keys, checks which locales are missing entries and syncs locale files; init --yes sets up non-interactively, and a bundled agent skill guides app internationalization. Needs a Node.js project using i18next.

Stape's Google Tag Manager MCP: lets agents view, create and edit tags, triggers and variables in GTM containers, for tracking and conversion setup. Hosted version (routes data via Stape's servers) needs just Google sign-in on first use; or run locally with a service account key.

Nulab's official Backlog MCP: lets agents manage Backlog projects, issues and comments, milestones and wikis, and view Git repositories and pull requests. Needs your Backlog space URL and a personal API key, plus Node.js or Docker.

Official Alpha Vantage MCP: exposes its API as tools for stock and options quotes, fundamentals, news sentiment, forex, crypto, commodities, economic indicators and dozens of technical indicators. Needs a free API key; a remote OAuth server is also available.

Comet's official Opik MCP: query traces and spans of LLM apps in chat, log scores and comments, and manage datasets, experiments and prompt versions. Works with Opik Cloud (API key or browser sign-in) and self-hosted open-source Opik.

Diagnoses page-load and interaction performance from Chrome DevTools traces, network evidence and source code, covering Core Web Vitals, LCP and layout shifts. Separates measured values from estimates and hypotheses, and re-measures fixes under equivalent conditions.