도구

Cross-platform shell built around structured data: pipelines pass tables instead of plain text, and you can open and query JSON, CSV, TOML and more directly. Default builds include nu --mcp, which serves it to agents as an MCP server.

Converts PDFs, images, PPTX, DOCX, XLSX, EPUB and more into Markdown, JSON or HTML, preserving tables, formulas and layout, with optional LLM help for higher accuracy. Needs Python 3.10+ and PyTorch; large-scale commercial use of the model weights needs a paid license.

Official Anthropic plugin that reads local session logs in ~/.claude/projects and generates an interactive HTML usage report covering tokens, cache hit rate, subagents, skills and the most expensive prompts, with optimization tips. Needs Node.js.

Designs and builds MCP servers: first picks a deployment model among remote HTTP, MCPB bundles and local stdio, then guides tool design, auth and in-chat interactive components. Maintained by Anthropic.

Connects Claude Code to the Pyright language server for static type checking and code intelligence in Python. Install pyright first with npm, pip or pipx. Official Anthropic plugin.

Creates or improves Agent Skills from scratch: writes eval cases to test them, runs benchmarks with variance analysis, and tunes descriptions for more accurate triggering. Maintained by Anthropic.

Browser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP.

ByteDance's open-source multimodal agent CLI: operates browsers via vision or the DOM and calls terminal, file and MCP tools to complete tasks, with a Web UI and headless server mode. Needs Node.js 22+ and a model API key.

Detects your CPU, memory and GPU and scores open models on whether they run, speed, quality and context, then works with local runtimes like Ollama, llama.cpp and MLX to download and benchmark them. recommend --json gives agent-friendly output.

Local model gateway that routes requests from Claude Code, Codex and other coding agents to providers like DeepSeek, Kimi, Gemini and OpenRouter, with failover, rule-based routing and request logs. Bring your own API keys.

Headless browser written from scratch in Zig for AI agents and automation, using less memory and running faster than headless Chrome in official benchmarks. fetch turns pages into Markdown, and it can serve CDP or MCP. Telemetry is on by default (an env var disables it); Windows needs WSL.

Lightweight command-line JSON processor that slices, filters, maps and transforms JSON with concise expressions and no runtime dependencies. A staple for agents parsing API responses and logs.

Trading research agent from HKU's HKUDS whose MCP server offers 70+ tools for quotes, financials, backtesting and research across A-shares, Hong Kong and US stocks and crypto. Needs local Python; HK, US and crypto research need no API key. For research only; not investment advice.

When a user asks whether a skill exists for some task, searches the skills.sh ecosystem with the skills CLI, then recommends and installs a fit. Maintained by Vercel Labs and shipped in the skills CLI repo.

Package manager for the open Agent Skills ecosystem: one command installs skills from GitHub and other sources into Claude Code, Codex, Cursor and dozens more agents, with search, update and removal. From Vercel Labs.

Official CLI for Tencent's open-source knowledge base platform WeKnora: upload documents, manage knowledge bases, run hybrid search and answer questions from them, or serve as a read-only MCP. Needs your own WeKnora deployment and a source build with Go 1.26+.

Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud.

Writes conversations and business data into Graphiti's temporal knowledge graph so agents can retrieve long-term memory by entity, fact and time. Open source from Zep; start FalkorDB or Neo4j and the server with Docker first, and configure an LLM API key.

Data analysis plugin: writes queries in each SQL dialect, explores datasets, runs statistical tests, charts with Python and builds interactive HTML dashboards, then reviews methods and conclusions before sharing. Connects to Snowflake, BigQuery and other warehouses. Official from Anthropic.

Anthropic's official data skill that guides agents to write, translate and optimize SQL across Snowflake, BigQuery, Databricks, PostgreSQL and other warehouse dialects, including CTEs, window functions and analytical aggregations.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.