Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Run one of the commands below, then add the client config underneath.
npmnpx -y agent-obs
Paste into Claude Desktop, Cursor (mcp.json), VS Code or any MCP client, then restart the client.
mcpServers{
"mcpServers": {
"agent-observability": {
"command": "npx",
"args": [
"-y",
"agent-obs"
]
}
}
}
Agent Observability is listed in the AI Agents category of the MCPNav directory. It is distributed as npm and can be loaded by any client that speaks the Model Context Protocol.
Typical uses include giving your assistant scoped access to the corresponding service so it can answer questions and take actions with real data instead of guessing. Always review what a server can access before you enable it — see our MCP security guide.
Agent Observability is an MCP server by KryptosAI. Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Install it with: npx -y agent-obs. Then add the JSON config to your client's MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/KryptosAI/agent-observability. Any third-party API it calls (such as a search or maps API) may require its own key and billing.
Any MCP-compatible client can use it, including Claude Desktop, Cursor, VS Code, Windsurf and custom agents.