Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
1–12 of 326 tools for “protocol”
Clear allReviewer rejection workflow and strict lockout semantics
official/skill/MIT/★ 5.4k in collection/no key
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.
node.js/MIT/★ 83/no key
Portable AI coding-agent skills for source-attributed, human-approved context packages.
skill/Apache-2.0/★ 9/no key
The open standard for agentic software verification: query business rules, assess release risk, and execute autonomous testing workflows.
skill/Apache-2.0/★ 18/no key
Your AI converges by default. This makes it diverge. Six Claude Code skills for AI-assisted divergent thinking, built on neuroscience.
skill/MIT/★ 12/no key
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows
mcp/link only/★ 107
PostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.
hosted by author/no license/no key
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
skill/MPL-2.0/★ 1.6k/no key
Find, prove and control the AI agents on your machines: discovers every agent and what it can reach, proves policies with Z3 + TLA+, enforces them deterministically outside the model.
python/Apache-2.0/★ 27/no key
A MCP server that gives LLMs direct access to the AT Protocol ecosystem, enabling seamless interaction with Bluesky and other AT Protocol-based social networks.
skill/MIT/★ 9/no key
A server implementation for the Model Context Protocol (MCP) in Ruby.
skill/MIT/★ 13/no key
Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.
skill/Apache-2.0/★ 38/no key
Who stands behind it
Who stands behind it
