AI-optimized GitHub MCP server: 112 tools, 98% token reduction, compact responses.
6,112 MCP servers
Production-ready MCP server for Cursor Background Agents API - enables LLMs to create, manage, and interact with Cursor's autonomous coding
MCP server (stdio): repair broken/malformed JSON via the AgentForge API
Compile messy document directories into Karpathy-style llm_wiki knowledge bases — standalone Q&A CLI + Claude Code/Codex skills
Validate, format, and inspect JSON locally. No network and no key.
Evidence-backed npm upgrade preflight and dependency audits for coding agents, paid via x402.
Checks and fixes ABAP Open SQL for SAP's ADT data-preview console. Connects to nothing.
67 semantic C#/.NET analysis tools via Roslyn: navigation, refactoring, codegen, audit.
MCP cron validator for AI agents; flags impossible schedules and other silent cron bugs.
Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold.
Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.
Turn any codebase into a queryable knowledge graph — offline-first, zero API keys.
Validate compact backend specs and generate tested NestJS, Prisma, and PostgreSQL repositories.
Explore the Claude Code CLI source — browse tools, commands, search code, and more.
Organize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop.
Team conventions, anti-patterns, and domain knowledge from .codehabits/ for AI coding agents.
Core MCP server for Context-Pods toolkit
Plan and verify multi-ecosystem packaging (Linux, Windows, macOS, HarmonyOS) for AI agents.
MCP server for cross-vendor API/SDK deprecation and breaking-change tracking
MCP server for Eclipse JDT.LS (Java Language Server), providing Java IDE features as MCP tools
A self-hosted VS Code workbench embedded as an interactive MCP App.