Explore
MCP servers and skills: search, filter by where they run, and compare.
mcp-claude-codeSDGLBL
Local
MCP servers and skills: search, filter by where they run, and compare.
MCP implementation of Claude Code capabilities and more
PythonMIT★ 305No key
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.
PythonMIT★ 52No key
An ultra-lightweight command-line AI coding assistant tool that mimics Cursor implementation. Elpis is an intelligent code assistant based on LangChain and OpenAI API that helps developers with code w
PythonMIT★ 2Few starsNo key
PythonMITFew starsNo key
Proof-carrying workflows for coding agents: bind tests to exact code, detect stale evidence, review scope, and hand proof across agents.
PythonMIT★ 2Few starsNo key
Local-first, explainable runtime policy gateway for AI tool calls
PythonMIT★ 1Few starsNo key
Agentic Firewall sits between an AI agent or MCP client and an MCP server. It can enforce runtime policies and automatically test the server's tool-use attack surface with 17 OWASP ASI scenarios. It r
PythonMIT★ 3Few starsNo key
An **MCP server** for the Gemini CLI that analyzes a local code repository (and helps generate and maintain a high‑quality `ONBOARDING.md` guide.
PythonMIT★ 2Few starsNo key
A governed execution layer between typed-decision models (TypeSafe Jev) and agent/AI tooling like Claude Code, MCP, and AI SDKs, turning probabilistic decisions into deterministic, policy-controlled,
PythonApache-2.0★ 2Few starsNo key
A naive, from-scratch implementation of an AI sandbox
PythonApache-2.0★ 1Few starsNo key
MCP server for Juniper/JUNOS — show, upgrade with rollback, config push (commit confirmed) with safe dry-run defaults, RSI/SCF collection
PythonApache-2.0★ 1Few starsNo key
Security contract testing, tool-poisoning detection, and drift gates for Model Context Protocol servers.
PythonApache-2.0★ 1Few starsNo key
Secure, context-confined command execution MCP server for VS Code
MCPLink only★ 1Few stars
Diagnose remote MCP connection failures for AI agents. Python CLI for protocol, TLS and OAuth checks plus ChatGPT/Claude compatibility findings; never executes server tools.
PythonMITFew starsNo key
Enterprise-grade Model Context Protocol servers for Claude AI - GitHub, Jira, Frappe ERP, file operations, bash execution, web access, and caching with production-ready CI/CD workflows
PythonMIT★ 2Few starsNo key
Governed execution layer for AI agents — MCP server with Y*gov runtime enforcement
PythonMITFew starsNo key
Developer preview: supervised AI agents for codebase analysis and reviewed changes. Python CLI/SDK, Node adapter, MCP, source citations and recoverable edits.
PythonApache-2.0Few starsNo key
Serving access to a JupyterHub as code interpreter sandbox for LLMs using MCP.
PythonMITFew starsNo key
A minimal, transparent PowerShell 7 MCP for Windows -- one tool: run a command, get raw exit code / stdout / stderr back.
PythonMIT★ 1Few starsNo key
PythonMIT★ 1Few starsNo key
Security scanner for AI skill files (SKILL.md) and bundled code (scripts/, tools/). It helps you catch high-risk patterns before publishing or running a skill.
SkillMIT★ 5No key
MCP server to drive CoppeliaSim 4.10 from Claude Code and other MCP clients — build scenes, joints and sensors, run the simulation and read it back. No arbitrary Lua execution.
PythonMIT★ 1Few starsNo key
Who stands behind it
