Claude.ai Agent Reliability Resource/agent-observability-standards
How to: Claude.ai Agent Reliability agent-observability-standards
Add Agent Reliability to Claude.ai
-
01
Open Settings → Connectors → Add custom connector and merge this in. Keep any servers already there.
https://agentreliability.dev/mcp?via=manifest-
02
Save the file and restart Claude.ai.
-
03
agent-observability-standards is surfaced wherever your client lets you attach context. It is context to attach, not an action to run.
-
04
If it does not appear, check that Agent Reliability is connected and that you are looking at its resources rather than its tools.
Claude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs
Same resource, other clients
Read from the server itself, by connecting to it and calling resources/list on 24 September 2026.
A listing does not declare its resources, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each resource's type and contents.