MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Runtime security platform for LLM agent tool calls on Kubernetes
PythonApache-2.0★ 26No key
MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.
PythonMIT★ 18No key
Pre-merge and pre-install trust checks for AI-agent skills and MCP configurations. Scan capabilities, detect risky changes, and block unapproved agent behavior in CI.
PythonMIT★ 2Few starsNo key
gVisor-isolated Kubernetes sandbox with an HTTP API, SDK and MCP bridge
PythonMIT★ 1Few starsNo key
橋守 the bridge keeper — a tiny, deterministic rules engine for AI use case governance. Policy in YAML, intake in JSON, decision in milliseconds, with an audit trail.
SkillMIT★ 6No key
🚪 Governance gate for AI agents. Enforce policies before deployment: request contracts, operational safeguards, identity boundaries, action budgets. CLI tool with YAML config, JSON/text output, CI/CD
PythonMIT★ 4Few starsNo key
The active firewall and execution governance gateway for AI agents. Run Cursor, Claude Code, Cline, and custom agents safely on your infrastructure with OPA/Rego policies, real-time risk scoring, tain
PythonMIT★ 2Few starsNo key
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
PythonApache-2.0★ 990No key
Config-driven automation for semantic versioning, conventional commits, and changelogs across Python, Node, Rust, and Go via CLI, GitHub Actions, and pre-commit hooks.
PythonMIT★ 1Few starsNo key
The first open-source effort estimation tool built for AI coding agents. PERT + METR + wave planning.
SkillApache-2.0★ 6No key
A typed judgment layer for Claude Code, Codex and Hermes Agent using TypeSafe's Jev: routing, verification, stop/continue and tool-call checks. Independent project.
SkillMIT★ 1Few starsNo key
An open-source, terminal-based AI coding agent that reads your code, calls tools, and helps you build.
PythonGPL-3.0★ 151No key
Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.
SkillMIT★ 344No key
Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients
PythonMIT★ 43No key
PyBun is a Rust-built, single-binary toolchain for Python. It delivers fast installs, lazy-import runtime, hot reload, a built-in test runner, builder, and MCP server with JSON-first output for AI age
PythonMIT★ 1Few starsNo key
Open-source agent simulation and runtime control platform for Claude Code
PythonApache-2.0Few starsNo key
90+ production-safe OpenStack tools for AI agents via MCP. Project-scoped & read-only by default. Works with Claude, Open WebUI & any MCP client. FastMCP + OpenStack SDK. Available on PyPI, Docker Hub
PythonMIT★ 45No key
K8s misconfiguration exploitation toolkit
PythonApache-2.0★ 4Few starsNo key
A Model Context Protocol (MCP) server for Apache Airflow 2.x and 3.x, built on the official MCP Python SDK.
PythonApache-2.0★ 1Few starsNo key
Drive the Pollen Robotics Microduck (sim) from any MCP client — with a live Agent Experience debug page
PythonApache-2.0★ 3Few starsNo key
Drop-in HTTP proxy for Ollama with priority queuing, per-client auth, and model-aware failover
PythonMIT★ 3Few starsNo key
Test your website the way a person uses it: plain-language goals, verdicts from the page. A CLI and an MCP server for people and AI agents.
PythonMIT★ 3Few 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
Who stands behind it
