Anthropic API Agent Skills

An MCP server that provides enriched blockchain data from Codex. This server can be used with any MCP-compatible client like Claude Desktop. To use the MCP Codex Server, you need to have a Codex API key. You can get your key from the Codex Dashboard. You can run the MCP Codex Server directly without installation using npx: Start the server using stdio (for embedding in CLI tools): For development

The stable, glowing orb at the center represents the persistent context that survives across chat sessions. The flowing data streams show how ongoing conversations connect to and draw from this stable core of information, preventing context loss. A static MCP (Model Context Protocol) server that provides AI models with persistent tool context, preventing context loss between chat sessions. This se

This MCP server integrates with Google Drive to allow listing, reading, and searching files, as well as the ability to read and write to Google Sheets. This project includes code originally developed by Anthropic, PBC, licensed under the MIT License from this repo. - gdrivesearch - Description: Search for files in Google Drive. - query (string): Search query. - pageToken (string, optional): Token

An integration that allows Claude Desktop to monitor and query the operational status of major digital platforms including AI providers, cloud services, and developer tools using the Model Context Protocol (MCP). - Monitor world's most used digital platforms (GitHub, Slack, Discord, etc.) - Track AI providers including OpenRouter, OpenAI, Anthropic, and Gemini - Get detailed status information for

Netresearch AI skill for assessing and enhancing software projects to meet enterprise-grade standards for security, quality, and automation. This is an Agent Skill following the open standard originally developed by Anthropic and released for cross-platform use. Supported Platforms: - ✅ Claude Code (Anthropic) - ✅ GitHub Copilot - ✅ Other skills-compatible AI agents - OpenSSF Framework Alignment -

An MCP server that lets AI assistants like Claude read LinkedIn data through your own logged-in browser session. Access profiles and companies, search for jobs, or get job details. This MCP server is free and open source, supported by Unipile. It runs locally with your own browser session. Unipile is the fully managed cloud alternative: a hosted LinkedIn API for Classic, Sales Navigator, and Recru

Welcome to the awesome-ai-research-writing project! This application helps you elevate your AI research writing without the usual hassle. Let’s guide you through the steps to download and run the application smoothly. 1. Visit the Releases page to download your copy of the software. 2. Choose the latest version available. Look for the asset that fits your operating system. 3. Click the download li

Stop pasting API keys into AI chat. When you paste sk-proj-xxx into Claude Code, that secret is now in your conversation history, Anthropic's logs, and potentially exposed to prompt injection attacks. secretctl fixes this. Your AI gets command results, never secret values. Every day, developers paste secrets into AI coding assistants: This is a security incident waiting to happen. - Secrets in con

A local-first CLI that orchestrates multi-agent AI workflows for software development. Give it a task — or feed it your specs, PRDs, and guidelines — and it coordinates specialized agents to architect, code, review, test, and ship automatically. No cloud dependency. Bring your own API keys. Your code stays on your machine. Each stage uses a specialized AI agent with tuned prompts and parameters. T

Own your AI. Agents, memory, tools, and identity that live on your Mac. Built purely in Swift. Fully offline. Open source. Download for Mac · Plugin Registry Models are getting cheaper and more interchangeable by the day. What's irreplaceable is the layer around them -- your context, your memory, your tools, your identity. Others keep that layer on their servers. Osaurus keeps it on your machine.

arvo-mcp is a Model Context Protocol (MCP) server that connects your AI assistant to Arvo, an AI-powered fitness coach. Access your workout history, personal records, body composition, and training plans directly from Claude Desktop, Cursor, or any MCP-compatible client. Perfect for fitness enthusiasts who want to: - 🏋️ Ask "What's my workout today?" and get your personalized training plan - 📊 T

Version: v0.2.0 An MCP server that provides access to the Postman API. Functionality is based on the official OpenAPI specification. For more information, see the Postman API documentation. This project is part of the Model Context Protocol (MCP) initiative from Anthropic. For more information, visit the MCP GitHub repository and the announcement on the Anthropic blog. Skip ahead to install instru

A remote Model Context Protocol (MCP) server that connects AI assistants to your crash reporting and real user monitoring data in Raygun through natural language conversations. 📚 Tool Reference • 🚀 Quick Start • 🔑 Get API Token - 🐛 Error Management - Investigate, resolve, and track application errors and crashes with full stack traces and context - 🚀 Deployment Tracking - Monitor releases and

Run your Miro workshops, retros, and planning sessions from the command line. Read boards, create stickies, organize frames, and generate diagrams through Claude, Cursor, or any MCP client. 98 tools | Single binary | All platforms | All major AI tools Homebrew (macOS/Linux): One-liner (macOS/Linux): Manual download: See SETUP.md for all platforms 1. Go to miro.com/app/settings/user-profile/apps 2.

Discover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".

This Model Context Protocol server implementation of Asana allows you to talk to Asana API from MCP Client such as Anthropic's Claude Desktop Application, and many more. More details on MCP here: - https://www.anthropic.com/news/model-context-protocol - https://modelcontextprotocol.io/introduction - https://github.com/modelcontextprotocol - ASANAACCESSTOKEN: (Required) Your Asana access token - RE

A Model Context Protocol (MCP) server for Database EKM/TDE operations using CipherTrust Application Key Management (CAKM). - Resource-Based Management: Tools are organized by the database objects they manage (e.g., keys, encryption, wallets), not just by actions. - Operational Grouping: Each tool exposes multiple operations (e.g., create, list, rotate) for comprehensive lifecycle management. - Uni

Built by Matious — We build custom AI tools and MCP servers for businesses. Managing Google Ad Manager is tedious. Creating campaigns, uploading creatives, and configuring line items involves countless clicks through a complex UI. This MCP server changes that. Connect it to Claude and manage your entire ad operations through conversation: - "Create a new campaign for Nike ending December 31st" - "

Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format. It provides a set of tools to transform PDFs, images, audio files, web pages, and more into easily readable and shareable Markdown text. - Convert multiple file types to Markdown: - Audio (with transcription) - Convert web content to Markdown: - YouTube video transcripts - Bing

Full documentation is available at buildkite.com/docs/apis/mcp-server. When using many MCP tools, context usage can become significant. The --dynamic-toolsets flag enables Anthropic's Tool Search pattern which marks most tools for on-demand loading. To use this feature: 1. Start the server with the --dynamic-toolsets flag: 2. Enable tool search in Claude Code by setting the environment variable: W

Also available in TypeScript Send requests to OpenAI, MistralAI, Anthropic, xAI, Google AI, DeepSeek, Alibaba, Inception using MCP protocol via tool or predefined prompts. Vendor API key required The server implements one tool: - unichat: Send a request to unichat - Takes "messages" as required string arguments - Returns a response - codereview - Review code for best practices, potential issues, a

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence.