# AI Agent Platform Developer Docs

> Connect agent clients, follow safe task recipes, understand permissions and approvals, and check supported client configurations.

- Human page: https://mailrith.com/developers/category/agent-platform
- Markdown page: https://mailrith.com/developers/category/agent-platform.md
- Guide count: 8
- Last updated: 2026-08-25
- Related keywords: AI Agent Platform, AI Agent Platform developer docs, Mailrith developer docs, Mailrith public API, Agents, AI Agent Quickstarts, AI Agent Architecture And Security, AI Agent Client Compatibility, AI Agent Examples, AI Agent Analytics And Compliance, AI Agent Supported Actions And Support, MCP Server

Agent notes:
- Use these category links to choose the most specific Mailrith developer guide before writing integration code.
- Use the OpenAPI document for exact request and response schemas.

## Guides
- [Agents](https://mailrith.com/developers/agents.md): Mailrith supports OAuth directory connections for ChatGPT, Codex, and Claude, plus a compact discovery stack with llms files, API metadata, OpenAPI, authenticated capabilities, SDKs, and MCP entry points.
- [AI Agent Quickstarts](https://mailrith.com/developers/agent-quickstarts.md): Start with the Mailrith plugin, the Mailrith Connector, or a scoped MCP connection. Then follow task-based paths for read-only, Broadcast, Sequence, and safe test-workspace workflows.
- [AI Agent Architecture And Security](https://mailrith.com/developers/agent-security.md): Mailrith uses one public resource model, least-privilege credentials, typed operations, existing delivery safeguards, request IDs, and current-resource verification across every supported agent client.
- [AI Agent Client Compatibility](https://mailrith.com/developers/agent-compatibility.md): The Mailrith plugin is available for ChatGPT and Codex, and the Mailrith Connector is available for Claude. Both use OAuth, while other supported clients can use scoped MCP connections.
- [AI Agent Examples](https://mailrith.com/developers/agent-examples.md): Each example demonstrates one safe Mailrith workflow, lists its required permissions, and keeps reads, retries, writes, and stored data bounded.
- [AI Agent Analytics And Compliance](https://mailrith.com/developers/agent-analytics-and-compliance.md): Use compact outcome reports and privacy-conscious diagnostics, then change real Mailrith resources through their task permissions and normal safeguards.
- [AI Agent Supported Actions And Support](https://mailrith.com/developers/agent-supported-actions.md): Use the current supported-actions matrix, understand operation terms, account for freshness and compliance boundaries, and troubleshoot without sharing secrets or Subscriber content.
- [MCP Server](https://mailrith.com/developers/mcp.md): The Mailrith Connector is available in Claude, and the same remote MCP server supports OAuth or protected server-side credentials for OpenAI, n8n, Pipedream, and other clients.