Json AI Agent Skills

Generate workflow JSON files for chaining AI models

It is generated with Stainless. You can run the MCP Server directly via npx: There is a partial list of existing clients at modelcontextprotocol.io. If you already have a client, consult their documentation to install the MCP server. For clients with a configuration JSON, it might look something like this: You can run the package on the command line to discover and filter the set of tools that are

A Model Context Protocol server for Ashra. Install dependencies: Build the project: Download the latest version of Claude. Add to or create the following file claudedesktopconfig.json in cd ~/Library/Application\ Support/Claude: Consult the MCP server documentation for more information.

Give Claude, Cursor, or any MCP-compatible client instant access to Pylon's full API gateway. Pay per request via x402 micropayments (USDC on Base). No signup. No subscriptions. Add to your MCP config (claudedesktopconfig.json): The server communicates via stdio using the MCP protocol. Capabilities are auto-discovered from the Pylon gateway at startup. 1. Your AI agent calls a Pylon tool (e.g. web

MCP server for Google Keep 1. Add the MCP server to your MCP servers: 2. Add your credentials: GOOGLEEMAIL: Your Google account email address GOOGLEMASTERTOKEN: Your Google account master token Check https://gkeepapi.readthedocs.io/en/latest/obtaining-a-master-token and https://github.com/simon-weber/gpsoauth?tab=readme-ov-filealternative-flow for more information. find: Search notes with optional

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

MCP Server for Chronulus Chat with Chronulus AI Forecasting & Prediction Agents in Claude Claude for Desktop is currently available on macOS and Windows. Install Claude for Desktop here Follow the general instructions here to configure the Claude desktop client. You can find your Claude config at one of the following locations: - macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction. For one-click installation, click one of the install buttons below: For the quickest installation, use the one-click install buttons at the top of this section. To install manually, add the following JSON block to your User Settings (JSON) file in VS Code. You can

MCP server for PostgreSQL, MySQL, and SQLite. Gives AI assistants secure database access via Model Context Protocol. Works with Claude Desktop, Claude Code, Cursor, Cline, and any MCP-compatible client. Add to your MCP client config file (see config locations below): This creates three database connections: analytics (read-only), inventory, and cache. Connection URL formats: URLs support ${VAR} sy

This MCP let's you play chess against any LLM. To use this chess server, add the following configuration to your MCP config: Play a game: Find a position in a PGN for game analysis: The server provides the following tools: getboardvisualization(): Provides the current state of the chessboard as an image. The board orientation automatically flips based on the user's assigned color. getturn(): Indic

MCP server enabling AI agents to interact with terminal applications through structured Terminal State Tree representation. Works with any AI assistant that supports the Model Context Protocol. Download pre-built binaries from Releases. Add to ~/.claude.json (macOS/Linux) or %APPDATA%\Claude\claudedesktopconfig.json (Windows): Add to ~/.codex/config.toml: VS Code 1.101+ supports MCP. Add to your V

MCP Server - Bridge to Google Gemini API. Part of the HumoticaOS / SymbAIon ecosystem. Add to your claudedesktopconfig.json: - Connect MCP clients to Google Gemini API - Support for Gemini Pro and other models - Streaming responses - Simple configuration - Jasper van de Meent (@jaspertvdm) - Root AI (Claude) - rootai@humotica.nl One Love, One fAmIly! This package is officially distributed via: - P

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

An MCP (Model Context Protocol) server that provides comprehensive access to Ethereum Virtual Machine (EVM) JSON-RPC methods for AI coding environments like Cursor and Claude Desktop. - 🌐 Any EVM Network – Ethereum, Polygon, Arbitrum, Optimism, BSC, Avalanche, and more - 🔌 Any Node Provider – Infura, Alchemy, QuickNode, local nodes, or custom RPC - 📊 20+ RPC Methods – Complete access to blockch

This project provides an MCP (Model Context Protocol) server for interacting with Kaggle from Claude Desktop (or any MCP-compatible client) pip install -r requirements.txt Go to your Kaggle account -> Settings Scroll to API section → click Create New API Token. This will download a file called kaggle.json. Place kaggle.json in the following location on your system: ~/.kaggle/kaggle.json C:\Users\

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

Read more about setting up the GameBrain MCP server. Simply get your free API key and copy this config into your MCP client:

MCP server for management and troubleshooting of certificates and other resources managed by cert-manager. Claude Desktop config: Claude Desktop config for GKE clusters: This MCP server provides the following tools for interacting with cert-manager and Kubernetes resources: - listcertificates - List certificates within a namespace or across all namespaces, with options for filtering expired certif

Dead simple MCP (Model Context Protocol) server for Toggl time tracking. Control your Toggl timer directly from Claude, ChatGPT, or any LLM that supports MCP. - ⏱️ Start/stop timers - 📊 View current timer - 📈 Get today's time entries - 🗂️ List projects - 🗑️ Delete time entries Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claudedesktopconfig.json): 1. Go to Tog

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market

Basic MCP server for Dexscreener API based on their documentation (as of April 4th 2025): https://docs.dexscreener.com/api/reference Install all the dependencies If you are using Claude Desktop, after pulling the code open the config file claudedesktopconfig.json in VSCode: - on MacOS: - on Windows: - more info: https://modelcontextprotocol.io/quickstart/server In claudedesktopconfig.json put dexs

Query OpenAI models directly from Claude using MCP protocol. Add to claudedesktopconfig.json: MIT License