도구

Official SonarSource server: connects to SonarQube Server or Cloud so agents can query code issues, quality gates, security hotspots and dependency risks, and analyze file contents directly. Needs a SonarQube token; Docker is the recommended way to run it.

Official Firecrawl skill: drives the Firecrawl CLI to search, scrape, map site URLs, batch-crawl, interact with pages and monitor changes, returning LLM-ready Markdown. Search and scrape have a rate-limited free tier; crawling and monitoring need an account or self-hosted instance.

Firecrawl's official CLI: scrape, search, map and crawl sites and interact with pages in a browser from the terminal, with Markdown output; can also install companion skills for coding agents. Needs a Firecrawl account or API key, or point it at a self-hosted instance.

Compares two versions of a LaTeX manuscript and produces a .tex that marks additions and deletions in color and strikethrough; compile it for a tracked-changes PDF to show reviewers, or diff versions from Git history. Ships with TeX Live and MiKTeX; needs Perl.

Searches about 30 biomedical sources, including PubMed, ClinicalTrials.gov, ClinVar and OncoKB, with one command syntax, covering literature, clinical trials, genetic variants, drugs and pathways. Ships as both a CLI and an MCP server.

Turns web pages, long PDFs, Word files, images or code into tutor-style study notes: Markdown notes plus searchable HTML knowledge cards with concept breakdowns and mind maps. Needs Python 3.8+, plus Chrome for some sites; the optional tutor chat needs an OpenAI-compatible API key.

Anthropic's official life sciences plugin marketplace: install MCP plugins such as PubMed, BioRender, Synapse, ChEMBL and 10x Genomics, plus research skills for single-cell RNA QC, Nextflow pipelines and scvi-tools. Some data sources need an account or subscription.

PubMed plugin from Anthropic's life sciences marketplace: connects to the US National Library of Medicine's remote MCP to search biomedical literature and research papers. No account needed.

Official BioRender plugin in Anthropic's life sciences marketplace: connects Claude Code to BioRender's scientific icons, templates and figures to find assets and make paper figures, lecture slides and talk graphics. Needs a free BioRender account; authorize it in /plugin after installing.

Plugin from Wiley in Anthropic's life sciences marketplace: connects the Scholar Gateway remote MCP for semantic search across Wiley's peer-reviewed journals, with answers carrying checkable citations and DOI links. Good for literature reviews. Needs a free Scholar Gateway account.

Anthropic's official research skill built on Fischbach and Walsh's problem-selection framework (Cell): a conversational guide to refining project ideas, assessing risk and success criteria, unblocking stalled research and choosing directions. No setup or account needed.

Redis's official MCP server: read and write strings, hashes, lists, streams, JSON and other data structures in natural language, with vector indexing and search and pub/sub. Bring your own Redis instance; runs via uvx.

Lets agents deploy a local folder or file contents straight to Google Cloud Run, list services and view their details and logs, and list or create GCP projects. Maintained by Google; sign in with gcloud and set up Application Default Credentials first.

Railway's official CLI: deploy with railway up and manage infrastructure config, with token auth for non-interactive CI runs. The installer can set up the Railway skill and MCP for Claude Code, Codex and others in one step. Needs a Railway account.

Official Docker skills: containerize projects, optimize and harden Dockerfile builds, orchestrate with Compose, use Docker Sandboxes and Docker Agent, with confirmation guardrails before deletes and other destructive actions.

Lets agents read dbt project models, lineage and Semantic Layer metrics, run build, run and test commands, and call the dbt platform Discovery and Admin APIs. Maintained by dbt Labs; Semantic Layer and platform tools need a dbt platform account.

DAIR.AI learning plugin that turns YouTube lectures and talks into local study material: extracts slide frames, builds timestamped transcripts, and lets you take notes and review in a bundled web viewer. Needs Python, yt-dlp and ffmpeg.

Official DuckDB skills: query local or S3 CSV, Parquet, Excel and JSON files with SQL or plain language, attach databases, convert formats, analyze spatial data and look up documentation. Needs the DuckDB CLI; tested only on macOS and Linux.

Elastic's official skills teaching agents to use Elasticsearch and Kibana correctly: index design, ES|QL queries, search relevance tuning, dashboards, observability troubleshooting and security alert triage. Currently a technical preview.

Manage Argo CD in natural language: list and inspect applications, create, update and delete them and trigger syncs, and view resource trees, workload logs and events. Maintained by Argo Project Labs; needs your Argo CD URL and an API token, with an optional read-only mode.

Chroma's official MCP: lets agents create and manage collections, add documents, and retrieve them with vector search, full-text search and metadata filters. Connects to in-memory or local persistent stores, self-hosted instances or Chroma Cloud.

33 cognitive-science-based tutoring skills for K-12 math and science, exam prep, university subjects, academic writing and job interviews, using Socratic questions and spaced review rather than giving answers. In Chinese and English; copy the skills folder into your agent manually.

Research workbench that turns paper PDFs into a searchable library so Claude Code or Codex can find and close-read papers, draft reviews and manuscripts, answer reviewer comments and check citations. Imports from Zotero and EndNote. Needs Python 3.10+; an LLM API key is optional.

Converts between Markdown, Word, HTML, LaTeX, EPUB and more with Pandoc, exports PDF and PPTX, and can apply a Word template for consistent styling, handy for formatting manuscripts and handouts. Needs Pandoc and uv; PDF export also needs TeX Live.