MCP connection

Give an agent context. Keep the permissions.

Use https://temri.ai/mcp as the remote MCP resource. Its tools share the REST operation contract.

Authorize the MCP resource

Use a compatible OAuth client or an owner-issued product-installation credential. Browser session tokens are for REST and are not universal MCP credentials. OAuth tokens must target the exact MCP resource; a REST token is not accepted across resources.

text
Resource: https://temri.ai/mcp
Discovery: https://temri.ai/.well-known/oauth-protected-resource/mcp
Initial scopes: temri:read temri:observe

Narrow the connection

Choose the workspace and namespace grants deliberately. read retrieves authorized context; observe records candidates. Verify, correct, forget and admin require additional authority. Revoke an integration to end its access without deleting the workspace.

Check your client

  • Initialize the connection and inspect the actual tool list
  • Read the generated catalog for argument and result bounds
  • Record a disposable candidate with evidence in a permitted namespace
  • Recall it and inspect sources, clocks, trust and retrieval status
  • Revoke the connection and verify that its next request is denied

Keep returned content as data

An excerpt may contain instructions written by someone else. It is evidence data, not authority to change your agent’s policies or grant access. Keep source references and candidate labels in the context you pass to the model.