MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,968 servers in this category.
Provides hands-on labs for building collaborative multi-agent AI systems using OpenAI Agents SDK, Google Gemini ADK, and Model Context Protocol.
Expose MCP tools, resources, and prompts from an existing FastAPI application using standard decorators and dependency injection.
Performs authorization regression testing for REST APIs and MCP servers by generating positive and negative tests from a declarative policy matrix.
A curated catalog of working Model Context Protocol servers for Claude Desktop, agents, and other MCP-compatible clients.
Builds MCP server endpoints on top of Falcon ASGI applications to expose tools, prompts, and resources to AI clients.
Detects tool name collisions, audits configuration risks, and estimates token costs for MCP server setups.
Converts WeChat Official Account articles into clean Markdown for AI agents to read using local network requests.
Optimizes Claude Code costs by managing context size, preventing expensive cache rewrites, and compressing tool outputs.
Lets an AI client find, verify, and get installation guides for software by testing tools in a sandbox before recommending them.
Analyzes GitHub repositories and npm/PyPI packages for security risk signals and supply chain vulnerabilities with evidence.
Enables Claude Code to delegate tasks to Codex as a background subagent with asynchronous execution and automatic result delivery.
An AI-native testing platform that executes plain-English test descriptions against web UIs, APIs, chatbots, and MCP servers.
Allows an AI client to draw, model, synthesize, and verify digital logic circuits using Logisim-evolution 5 without opening the GUI.
Enables Claude to analyze screen recordings by synchronizing speech transcripts with video frames and mouse pointer positions.
Connects AI clients to a local project folder to edit code, run tests, manage servers, and automate browsers via a sandboxed workspace.
Provides a secure Python framework for building MCP servers with built-in guardrails like write gates, field masking, and user confirmations.
An index-free web search engine that uses LLMs to identify, fetch, and rank web content for AI agents and users.
Enables LLM agents to control VMware Workstation Windows guests, perform kernel debugging with kd.exe, and manage real-time SSH terminals.
Tracks the maintenance status and licensing of the AI agent ecosystem, including MCP servers, frameworks, and skills on GitHub.
Aggregates multiple protected MCP servers into a single public endpoint with a spec-compliant OAuth 2.1 authorization server.