MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,969 servers in this category.
Provides a simple ping tool that responds with pong to demonstrate MCP Bundle packaging and distribution.
Allows an AI client to explore Copick project data and discover or validate CLI commands for building processing pipelines.
Scans LLM agentic workflows to visualize them, list their tools and MCP servers, and map vulnerabilities in an HTML report.
Provides an OpenAI-compatible endpoint that forwards requests to an inference engine and executes MCP tools on its behalf.
Lets an AI client run terminal commands on a Kali Linux machine for penetration testing, CTF solving, and security tooling.
Concierge is an SDK for building MCP servers that lets you expose only relevant tools at each step of your workflow.
Executes Python code in isolated rootless containers to discover and call MCP tools, reducing context window bloat.
Extracts encryption keys from WeChat 4.0 memory to decrypt local databases and provides real-time message monitoring and AI-driven chat querying.
Lets developers define, run, and secure portable AI agents from configuration, with built-in MCP and A2A support.
Enables AI clients to perform mesh analysis, repair, smart retopology, and 3D printability checks on 3D models.
Lets an AI client query and manage 40+ databases through DMS with SQL execution, NL2SQL, schema browsing, and approval workflows.
Indexes a local codebase and lets an AI client run semantic code, docs, and Git history searches offline.
$claude mcp add code-memory -- uvx code-memory
Lets an AI client read Qonto organization details, account balances, and transaction history for a business bank account.
A Claude Code plugin that enforces architectural decision-making by teaching concepts and requiring user approval before writing load-bearing code.
Provides a community-maintained directory of plugins, MCP servers, and skills to extend Claude Code and Cowork capabilities.
Provides on-demand loading of over 15,000 specialized skills for AI coding assistants to keep context windows lean.
Provides defensive security playbooks and hardening skills for LLM coding agents across web, infrastructure, and AI domains.
An open-source desktop coding agent for macOS that uses local models or API keys to perform tasks in isolated environments.
Automates the setup of Kiro IDE workspaces by writing agents, skills, commands, hooks, and MCP configurations into a project directory.
Allows AI agents and users to remotely control a real Amiga computer via a high-performance remote desktop interface.