MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. Bu kategoride 13.985 server.
GitHub reposunu yapıştırın, hızlı bir incelemeden sonra listeleyelim.
Sunucu gönder
Benchmarks static analyzers on real, publicly disclosed vulnerabilities in open-source MCP servers using Docker and SARIF scoring.
Provides shared task state, source-backed memory, and executable completion checks for AI coding clients like Claude Code and Cursor.
Provides an offline, end-to-end test environment to validate the Commonpost MCP for Thunderbird extension using real Thunderbird instances and containers.
Enables AI agents to orchestrate Unreal Engine scene construction through a controlled eight-stage workflow driven by reference images.
Provides a self-hosted gateway to connect AI agents to files, shell commands, and SSH targets on remote or local machines.
Provides a secure MCP tool service featuring three-layer SQL guardrails, JWT-based tool scoping, and a Text2SQL state machine.
Scans MCP tool declarations for security risks like command injection, secret exposure, and improper tenant boundaries.
Provides a secure local broker for agents to request secrets that are pasted into the user's OS keystore without the agent ever seeing the actual value.
Allows AI agents to inspect Unreal Engine installations, verify projects, and search local Fab asset libraries.
Scans MCP servers and tool-using agents for security vulnerabilities, drift detection, and injection paths with SARIF and HTML reporting.
Reproduce, compare, and minimize Model Context Protocol failures using deterministic scenarios and portable evidence.
Provides an intelligence layer for AI agents to build, test, debug, and verify Roblox games using official documentation and verification receipts.
Provides local, read-only codebase evidence to AI agents like Claude and Microsoft 365 Copilot to assist with code investigation and changes.
Provides Python primitives for implementing confirmation gates, structured error responses, and read-only tool filtering in MCP servers.
Provides a unified dashboard to manage, track, and update Claude Code skills, plugins, and MCP servers in a single table.
Integrates OpenAI Codex into Claude Code to delegate code reviews, plan validation, refactors, and implementations using specialized model routing.
Turns a Linux desktop into an MCP server that allows AI agents to run shell commands, manage tmux sessions, and operate the GUI via virtual input.
Allows an AI client to search Revit API documentation and 15 years of The Building Coder blog posts for technical details and code remarks.
Provides a live workbench to compare agentic, deterministic, and policy-driven enterprise workflows using LangGraph and MCP tools.
Evaluates tool-using agents by scoring every step of their interaction with an MCP server, including tool selection, arguments, and grounding.
