AI Agent Platform
Connect agent clients, follow safe task recipes, understand permissions and approvals, and check supported client configurations.
Agents
Discover Mailrith from agent runtimes with llms files, API metadata, OpenAPI, and authenticated capability discovery.
AI Agent Quickstarts
Connect a read-only agent, manage a Broadcast, and test the workflow in a dedicated workspace.
AI Agent Architecture And Security
Understand Mailrith's agent architecture, trust boundaries, permissions, OAuth, result verification, and troubleshooting flow.
AI Agent Client Compatibility
Check reviewed OpenAI, Claude, Codex, n8n, and Pipedream connection shapes, task-specific configurations, known limitations, and conformance rules.
AI Agent Examples
Use small reporting, Subscriber sync, and complete Broadcasts examples with focused Work Profiles and bounded work.
AI Agent Analytics And Compliance
Build a bounded analytics, diagnostics, and Subscriber subscription loop without bypassing Mailrith safety controls.
AI Agent Supported Actions And Support
Check read, draft, test, execute, and unsupported states, then use exact permission, approval, provider, and support guidance.
MCP Server
Connect Mailrith to agent runtimes through the official remote MCP server and streamable HTTP transport.