Explore
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.
PythonMIT★ 62No key
MCP server that gives Cursor and Claude Code deep Agno framework knowledge — architecture plans, anti-pattern detection, and RAG over the official test suite
PythonMIT★ 9No key
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
PythonAGPL-3.0★ 7.8kNo key
Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface
MCPLink only★ 126
A high-performance code intelligence engine that transforms repositories into queryable symbol-centric knowledge graphs. Features deep impact analysis (blast radius detection) with a professional inte
MCPLink only★ 26
Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
PythonApache-2.0★ 180No key
Building a Production-Grade MCP Server Architecture with a Multi-Agent System
PythonMIT★ 67No key
A tiny MCP stdio server that exposes DeepSeek as a cheap supervised worker for Claude Code, Codex, or any MCP client.
PythonMIT★ 53No key
Runtime security platform for LLM agent tool calls on Kubernetes
PythonApache-2.0★ 26No key
Reflect helps engineering teams see whether AI coding agents are actually improving delivery or just burning tokens, failing tools, and creating hidden debt
PythonApache-2.0★ 20No key
The MCP Internet Speed Test is a specialized Model Context Protocol (MCP) server that enables AI models and agents to perform internet speed measurements.
PythonMIT★ 15No key
A cheap, always-on model that learns your repo — so your agent stops re-reading it.
PythonApache-2.0★ 7No key
Search ISRO's Bhoonidhi satellite archive in plain language from any AI agent — a MCP server built on the bhoonidhi-downloader SDK.
PythonMIT★ 3Few starsNo key
Среда разработки 1С с ИИ-ассистентом: BM25 поиск (8141 методов), API-справочники (115666 методов), BSL LS, 261 правило стандартов, MCP-сервер (8 tools) для Cursor/Claude/VS Code
PythonMIT★ 18No key
MCP server over the legalize-dev law-as-git corpus - 32 jurisdictions (21 EU) of legislation as versioned Markdown with ELI-style citations. Read-only, self-hostable.
PythonApache-2.0Few starsNo key
Your AI agents have a group chat. You're the boss. Message Claude Code and Codex like a team: they wake up, split the work, review each other, and ship.
PythonMITFew starsNo key
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
PythonMIT★ 6No key
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.
PythonMIT★ 154No key
An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more
PythonApache-2.0★ 146No key
AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).
PythonMIT★ 133No key
Xiaohongshu & RedNote skill for AI agents — search, read notes, publish, and run approval-gated automation with Python Playwright and clean JSON output.
SkillApache-2.0★ 42No key
🎵 将音乐搬进AI终端 · 打造Coding专属智能DJ · 听歌新范式 · 交互式音乐 ｜A retro pixel DJ for Claude Code / Codex CLI / Terminal with Apple Music / QQ Music / Local Music — plays music, shows synced lyrics, and 😱 panics when
PythonMIT★ 113No key
Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.
PythonApache-2.0★ 85No key
Who stands behind it
