Self-run
MCP
Mcp Observatory
Test, secure, and monitor MCP servers before agents depend on them.
0
37
Free Self-run
MCP
Agent Observability
Trace AI agent execution: every tool call, every error, every dollar. Open source agent observability for Claude, Cursor, opencode, and any MCP-compatible agent. Local-first, free forever.
0
35
Free Self-run
MCP
Mcp Seatbelt
Runtime guardrails for AI agent MCP tools. Blocks dangerous tool calls at runtime with a default-deny policy proxy.
0
23
Free You've reached the end · 3 loaded