# AI Agent Client Compatibility > Use the current compatibility matrix and read-only starter configurations, then record live conformance against an exact client build or review date before making a support claim. - Human page: https://mailrith.com/developers/agent-compatibility - Markdown page: https://mailrith.com/developers/agent-compatibility.md - Category: AI Agent Platform - Reading time: 8 min read - Last updated: 2026-08-01 - Related keywords: AI Agent Client Compatibility, AI Agent Client Compatibility developer docs, AI Agent Platform, AI Agent Platform developer docs, Mailrith developer docs, Mailrith public API, Supported Client Matrix, Copyable Configurations, Known Limitations, Conformance And Support, MCP Server, AI Agent Architecture And Security, AI Agent Examples ## AI Agent Notes - Use this page as implementation guidance, then validate exact endpoint fields against the OpenAPI document. - Keep API keys server-side and workspace-scoped unless a guide explicitly says otherwise. - Do not invent privacy, consent, or lawful-basis evidence. Send only fields that appear in the OpenAPI schema for the endpoint you are using. ## What this guide covers Check reviewed OpenAI, Claude, Codex, n8n, and Pipedream connection shapes, task-specific configurations, known limitations, and conformance rules. ## Supported Client Matrix Mailrith supports exact conformance-reviewed connection shapes rather than claiming every past and future client release. Rolling client evidence expires after 90 days or immediately after a material MCP or authorization change. - ChatGPT and Codex plugin: the public 1.0 package and hosted MCP endpoint are published with OAuth, the shared Agent Skill, write approval, and the fixed submitted catalog. The OpenAI directory draft was started July 27, 2026, and directory review is pending. - OpenAI Responses API: remote MCP, Bearer authorization, write approval, and exact submitted-tool filtering. Template reviewed July 26, 2026. - Claude Connector: the public 1.0 package and hosted MCP endpoint are published with OAuth, the fixed submitted catalog, and shared reviewer prompts. Directory submission requires a Claude Team or Enterprise organization with directory-management access. - Claude Messages API: `mcp-client-2025-11-20`, remote server authorization, and exact MCP toolset allowlisting. Template reviewed July 26, 2026. - Codex CLI and app: Streamable HTTP MCP, OAuth login or a Bearer-token environment variable, and enabled-tool allowlisting. Template reviewed July 26, 2026. - Cursor plugin: the public 1.0 package and hosted MCP endpoint are published with OAuth and the shared Agent Skill. The Cursor publisher application was submitted July 27, 2026, and Marketplace review is pending. - n8n: inactive starter workflow using HTTP Request node 4.3, secret-backed Bearer authentication, and a bounded capability read. - Pipedream: Node.js component starter with a secret property, bounded capability read, and no write side effect. ## Copyable Configurations The versioned connector templates ship with the Mailrith Agent Skill package. Each template contains unresolved secret placeholders and starts read-only or disabled. Resolve secrets in the client at runtime and expand tool access only after reviewing the task. **Remote MCP Connection** ```text Name: Mailrith Transport: Streamable HTTP URL: https://api.mailrith.com/mcp Authentication: OAuth (preferred) or Bearer token from a secret store Initial tools: discovery_get_capabilities, workspace_get, subscribers_list, subscribers_get Provider confirmation: Disabled for the read-only starter ``` **Task-Specific Toolsets** ```text Read-only: discovery_get_capabilities, workspace_get, and the exact focused read tools needed Drafting: focused list, get, create, update, preview, and preflight tools Live send: the Broadcasts Work Profile plus broadcasts_send and broadcasts_get_send_progress Use a dedicated Broadcast-operation credential and an idempotency key. ``` ## Known Limitations The npm, PyPI, CLI, MCP, and Agent Skill packages are released together. Use the stable version named in the release manifest, and do not mix package versions from different releases. OpenAI, Claude, Codex, n8n, and Pipedream change independently. Re-run conformance after client authentication, MCP, tool approval, or workflow export fields change. n8n and Pipedream starters use stable HTTP primitives for the first read because third-party MCP node formats may change independently. Add writes only with task-specific credentials. Mailrith does not copy agent operations into a separate history. Confirm changes from the saved resource or its progress endpoint. Mailrith cannot verify claims generated by a model or replace the sender's legal, consent, deliverability, or provider responsibilities. ## Conformance And Support Repository conformance validates discovery, authentication, tool listing, a bounded read, draft behavior, scoped execution, resource verification, and connector-template safety. Live client runs must record the exact client build or review date and must use a dedicated workspace with no real Subscribers for early write tests. > Live OpenAI, Claude, Codex, n8n, and Pipedream conformance remains a release gate until the results are recorded against deployed endpoints. **Repository Conformance** ```bash pnpm agent:clients:conformance -- --profile static pnpm agent:clients:conformance -- --profile read --client codex --json ``` ## Related Guides - [MCP Server](https://mailrith.com/developers/mcp.md): Mailrith's official MCP server is the highest-level interface for agent runtimes. This page covers the remote endpoint and includes copy-paste examples for OpenAI, Claude, n8n, and Pipedream. - [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 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.