ツール

Official skills from US broker Alpaca: teach agents to backtest, place and check paper trades, plus developer guides for Broker API account opening, funding and reconciliation. Needs an Alpaca API key (paper trading uses no real money) and the Alpaca CLI; results need professional review.

Microsoft Translator's translation quality tool: GPT scores each sentence using MQM error categories or a direct score; --list_mqm_errors shows error types and severity. Needs line-aligned source and target files, Python and an OpenAI or Azure OpenAI key (paid); a translator should still review.

Connects any FHIR-compliant EHR server (e.g. the Epic sandbox or HAPI) to agents to search, read, create and update patient clinical data in plain language, with SMART on FHIR auth. By WSO2. Needs a FHIR server URL, access token and uv; clinicians must review results.

Alibaba Cloud's official ops MCP: manage ECS, RDS, OSS, VPC and other resources in plain language, view CloudMonitor metrics, and analyze a project and deploy it to ECS. Needs an Alibaba Cloud AccessKey and uv.

Tencent Cloud's official CLI: call any Tencent Cloud API by product and action name to manage resources (e.g. tccli cvm DescribeZones), with multiple profiles, role credentials and JSON or table output for scripting. Needs a SecretId and SecretKey.

Connects to a running Archicad and exposes 190+ commands from the Tapir add-on and the official JSON API, for querying walls and other elements, batch-editing models and exporting files. Needs Archicad (Windows or macOS), Tapir and uv. Alpha: it edits the open project directly, so back up first.

Lets agents inspect Alibaba Cloud ACK clusters, run kubectl operations, query Prometheus metrics, control-plane and audit logs, and run resource diagnostics and health checks. Maintained by Alibaba Cloud; needs an AccessKey and cluster RBAC permissions.

Jenkins plugin that turns Jenkins itself into an MCP server: agents can list jobs, trigger and rerun builds, page through and search build logs, and view test results and SCM info. Hosted in the official jenkinsci organization; authenticates with a Jenkins API token over Basic auth.

Sonar's official plugin bringing SonarQube checks into the agent coding loop: secrets-scanning hook, issue fixing, quality gates, coverage and dependency risk; with Vortex analysis on, every edit is checked. Needs SonarQube (free Community Build works), the sonar CLI and Docker.

From Twilio Labs: exposes Twilio's public APIs (SMS, voice, phone numbers, Serverless and more) as MCP tools generated from its OpenAPI specs, with filtering by service or tag. Needs a Twilio API key; marked as a proof of concept.

Shapes the agent's own replies rather than your documents: separates what changed from what was verified, cuts invented confidence, leads with the action and keeps load-bearing caveats. Manually invoked and stays on until you say stop; a script can enable it in CLAUDE.md or AGENTS.md.

Neon's official plugin combining the Neon MCP and skills to manage serverless Postgres: projects and branches, object storage, Functions and the AI Gateway. Signs in to Neon via OAuth the first time you use the MCP.

Connects to GeoServer's REST API so agents can manage workspaces, data stores, layers and styles, run CQL spatial queries, and access features and render maps via WMS/WFS, for publishing and maintaining map services. Needs a running GeoServer with an admin account, Python 3.10+ and uv.

PostHog's official plugin with a built-in MCP and 30+ skills: query product analytics, feature flags, A/B experiments, dashboards and error tracking from chat, and optionally send Claude Code sessions to LLM Analytics. Needs OAuth sign-in with a PostHog account.

Analyzes your codebase and generates a render.yaml Blueprint, or creates services directly through the Render MCP, to deploy apps to Render. Maintained by Render and included in OpenAI's curated skills. Needs a Render account and code pushed to GitHub, GitLab or Bitbucket.

MLflow's official skills plugin: lets coding agents add MLflow Tracing to LLM apps, analyze failed traces, build evaluation datasets and scorers, and query token and latency metrics, closing the instrument, evaluate, iterate loop. Needs MLflow 3.8+.

Pulumi's official skills: Pulumi program best practices, components and the Automation API, ESC secrets and config, debugging failed pulumi up runs, and migrating from Terraform, CDK, CloudFormation or ARM to Pulumi.

Pulumi's official plugin marketplace: write infrastructure as code in TypeScript, Python, Go and more, migrate from Terraform, CDK, CloudFormation or ARM, and manage ESC secrets and config. Works with both Claude Code and Codex.

Prisma's official skills: the Prisma ORM CLI, Client query API, connection setup for various databases, a v6 to v7 upgrade guide, and deployment workflows for Prisma Postgres and Compute.

Pinecone's official plugin: bundles the Pinecone MCP server and /pinecone skill commands to create vector indexes, upsert data, search in plain language, or build a document Q&A assistant with citations from Claude Code. Needs a Pinecone API key (free sign-up); Assistant features also need uv.

HashiCorp's official MCP: lets agents manage Vault mounts, read and write KV secrets, enable PKI, create issuers and roles, and issue certificates. Needs a reachable Vault server and token; HashiCorp recommends using it only in trusted local environments.

Trivy's MCP plugin: lets agents scan local projects, container images and remote repositories for vulnerabilities and misconfigurations in plain language, optionally checking policy compliance via the Aqua platform. Requires Trivy; maintained by Aqua Security.

Helps agents add Auth0 authentication to apps: detects 35+ frameworks and covers login, MFA, SSO, RBAC, JWT validation, migration from other auth providers, and tenant security audits. Maintained by Auth0; needs an Auth0 account (free sign-up).

Bentley's official MCP: lets agents drive a running STAAD.Pro structural analysis session to define load cases, set member properties in bulk, extract model data and read or write CSV/Excel. Needs Windows 11+, STAAD.Pro 2025 or later open, and uv. A structural engineer must review results.