MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,951 servers in this category.
Provides a security and governance layer for AI agents to control identity, policy, approvals, and threat detection for tools and MCP servers.
Provides a comprehensive course to design, build, test, and deploy AI agents using Python and real-world tools.
Exposes a secure to-do list via MCP tools for use with LangChain agents, FastMCP clients, and IDEs like VS Code.
Exposes multiple MCP servers through a single code API, allowing AI clients to execute sandboxed JavaScript to chain tools and reduce context usage.
Provides test vectors and reference implementations to verify MCP tool definition pinning and compliance with RFC 8785.
Performs static security triage on MCP server configurations to identify secrets, dangerous tool exposures, and prompt injection risks.
Provides a Unity 6 starter kit that enables AI agents to control the Unity Editor and Blender via MCP for automated game development.
Manages the lifecycle of local MCP servers on Windows by cleaning up idle backends and monitoring resource usage.
Provides a lifecycle toolkit and pre-flight checklist for building, testing, and publishing MCP servers.
Integrates committed work from multiple AI coding agents through a local Git merge queue with automated validation and durable receipts.
Provides a first-principles engineering guide to AI mechanisms like embeddings, RAG, and MCP using standard-library Python.
Allows an AI agent to explore GitHub repositories, inspect issues, pull requests, and repository activity through conversational queries.
Provides a real-time telemetry dashboard and terminal visualizer to monitor tool mesh routing, token economies, and MCP server health.
Enforces security boundaries for AI agents by validating tool calls against allowlists, fingerprints, scopes, argument rules, and egress controls.
Syncs Slack, GitHub, and Notion into a local knowledge graph to provide searchable team memory for AI clients like Claude and Cursor.
Audit MCP servers by generating scored reports on transport, session management, and schema compliance.
Performs black-box cross-validation of MCP servers by launching them as real processes and testing JSON-RPC 2.0 compliance across stdio and HTTP.
Provides hands-on AI engineering projects and an MCP server that routes prompts between Claude, Gemini, and local Ollama models.
Analyzes MCP servers by executing them in an isolated Docker sandbox to confirm and reproduce implementation vulnerabilities like SSRF and command injection.
Enables AI clients to inspect schematics, perform PCB auto-layout and routing, check DRC, and export manufacturing files within EasyEDA.
