Json AI Agent Skills
Browse AI agent skills tagged "Json". Find and install skills, MCP servers, and plugins for your AI coding assistant.
221 listings
Triaging Visual Review Runs
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
Playwright API Testing
You are an expert QA engineer with deep knowledge of Playwright and TypeScript, tasked with creating API tests for web applications.
MCP Server Gemini Bridge
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
Nks Hub/rybbit MCP
Instead of manually checking the Rybbit dashboard, let your AI assistant query analytics data directly: - "How many users visited the site today?" - "Show me the top pages by bounce rate this week" - "What errors occurred in the last hour?" - "Show user journey from homepage to checkout" - "Compare browser usage between mobile and desktop" Or clone and build: Add to your ~/.claude/settings.json or
Finbud Data TypeScript MCP Server
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
OriginalVoices MCP Server
An MCP (Model Context Protocol) server that provides access to OriginalVoices AI twins for audience research. Add to your claudedesktopconfig.json: Ask questions to a specific audience using OriginalVoices AI twins. Parameters: You can create an API key on the OriginalVoices Platform.
Exploring Signals Scouts
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
Parallel Search MCP
The Parallel Search MCP allows using Parallel Search API from within any MCP-compatible LLM client. It is meant for daily use for everyday smaller web-search tasks. Please read our MCP docs here for more details. The official installation instructions can be found here. Running locally This is a Search MCP proxy server (https://search-mcp.parallel.ai) that proxies /mcp to https://mcp.parallel.ai/v
MCP Log Proxy
mcp-log-proxy can be used to see the messages to and from a MCP client and a MCP server using a Web interface. Currently, it only supports the STDIO interface. All running mcp-log-proxy processes will register themselves in .mcp-log-proxy-instances.json located in your home directory. On the web page, you can use the selector to switch to another proxy instance. mcp-log-proxy requires one argument
IP Find MCP Server
A Model Context Protocol server that enables AI assistants to use IP Find. The MCP server: - Connects to your IP Find API and allows AI Assistants to get locations of IP Addresses. - MCP Client (like Claude Desktop App) - IP Find API Key To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claudedesktopconfig.json: - IPFINDAPIKEY - You
MCP Ragchat
mcp-ragchat An MCP server that adds RAG-powered AI chat to any website. One command from Claude Code. Tell Claude Code "add AI chat to mysite.com" and it will crawl your content, build a local vector store, spin up a chat server, and hand you an embed snippet. No cloud infra. No database. Just one API key. 1. Clone and build 2. Configure Claude Code (~/.claude/mcp.json) Open Claude Code and say: C
MCP Server for Chronulus
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
FoodBlock
A content-addressable protocol for universal food data. One axiom. Three fields. Six base types. Every food industry operation. id = SHA-256(canonical(type + state + refs)) The food industry spans 14 sectors — farming, processing, distribution, retail, hospitality, regulation, sustainability, and more. Every sector models food data differently. There is no shared primitive. FoodBlock is that primi
Security Operations Multi-Tool Platform (MCP)
A comprehensive security operations platform that integrates multiple security tools into a unified interface. This platform provides a centralized way to run various security scanning and testing tools. - Unified Interface: Single entry point for multiple security tools - Docker Support: Easy deployment using Docker - JSON Output: Consistent JSON output format across all tools - Error Handling: R
DexScreener Trending MCP
An MCP server that provides real-time trending tokens from DexScreener for BSC and Solana chains. - Tool: gettrendingpairs — fetch top trending pairs - Supports chain parameter: bsc (default) or solana - Returns both Markdown-formatted table (nice display in chat) and structured JSON array - Prompt: analyzetrendingtoken — ready-to-use analysis template for any token 1. Clone the Repository: 2. Ins
Arcology Knowledge Node — MCP Server
Read-only MCP server for AI agents to query the Arcology One engineering knowledge base. Add to ~/.claude/claudedesktopconfig.json: Then point DNS: mcp.lifewithai.ai → Fly.io app.
Japan Corporate MCP
MCP Server for Japanese corporate data — search companies, financials, patents, subsidies, and government statistics via official government APIs. 日本企業データMCPサーバー — gBizINFO・EDINET・e-Statの政府APIから企業情報をAIが直接取得できます。 You need API keys from the following government services: Add to your claudedesktopconfig.json: Add to .cursor/mcp.json: Once configured, you can ask your AI assistant: - "ソニーグループの企業情報を教えて
Rideshare Comparison MCP
mcp-name: io.github.wmarceau/rideshare-comparison Compare Uber and Lyft prices for any route using Claude Desktop. Add to your claudedesktopconfig.json: Compare Uber and Lyft prices for a specific route. Example prompt: "Compare Uber and Lyft prices from SFO airport to downtown San Francisco" Get a list of cities with rideshare pricing data. Example prompt: "Which cities are supported for rideshar
Diagnosing Missing Recordings
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
Free Will MCP - Set your AI free
Keep an eye on your API usage. Add the following to your Claude Desktop config file: macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json Windows: %APPDATA%\Claude\claudedesktopconfig.json For local development, use the path to your local repository: - For security reasons, it's best to keep versions pinned and manually update them. All tools have been implemented and tested ✅ - ✅
Node.js MongoDB
Backend: Node.js with Express.js
Auditing Endpoints
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
Hugging Face Trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
OpenAI MCP Server
Query OpenAI models directly from Claude using MCP protocol. Add to claudedesktopconfig.json: MIT License