# AI Agent Client Compatibility



> 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.



- 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: 2026-08-25

- Related keywords: AI Agent Client Compatibility, AI Agent Client Compatibility developer docs, Mailrith ChatGPT plugin, Mailrith Codex plugin, Mailrith Claude Connector, ChatGPT email marketing plugin, Codex email marketing plugin, Claude email marketing connector, Mailrith plugin installation, Claude Connectors Directory, AI Agent Platform, AI Agent Platform developer docs, Mailrith developer docs, Mailrith public API, Supported Client Matrix, Install The Mailrith Plugin In ChatGPT Or Codex, Connect Mailrith To Claude, 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.

- The Mailrith plugin is available from the universal plugin directory shared by ChatGPT and Codex, and the Mailrith Connector is available from Claude's Connectors Directory.

- Open the Plugins tab to install Mailrith. In Codex CLI, enter `/plugins` to install it. After installation, start a new ChatGPT chat or Codex session.

- In Claude, open `Customize` > `Connectors`, select the `+` button, choose `Browse connectors`, choose `Mailrith`, and select `Connect`.

- The Codex IDE extension does not support plugins.

- Both directory connections use OAuth. Sign in to Mailrith, choose one workspace, review the requested permissions, and select `Allow Access`.

- Other user-facing clients can connect to Mailrith's remote MCP server through OAuth. A trusted server-side runtime can use a task-specific workspace API key stored in a secret manager.



## What This Guide Covers

Install the Mailrith plugin in ChatGPT or Codex, connect the Mailrith Connector in Claude, and compare safe setup options for other supported AI clients.



## 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: available to install from the universal plugin directory in ChatGPT and Codex. It connects through OAuth to Mailrith's hosted MCP endpoint and includes the Mailrith Agent Skill, focused tools, and write approval.
- OpenAI Responses API: remote MCP, Bearer authorization, write approval, and exact tool filtering.
- Claude Connector: available to connect from Claude's Connectors Directory. It uses OAuth to connect one Mailrith workspace to the same focused tool catalog.
- Claude Messages API: `mcp-client-2025-11-20`, remote server authorization, and exact MCP toolset allowlisting.
- Codex CLI and app: install the Mailrith plugin, or connect through Streamable HTTP MCP with OAuth login or a Bearer-token environment variable and enabled-tool allowlisting.
- Cursor plugin: the public package connects to the hosted MCP endpoint through OAuth and includes the shared Mailrith Agent Skill.
- 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.

## Install The Mailrith Plugin In ChatGPT Or Codex

Mailrith is available in the universal plugin directory for ChatGPT and Codex. The plugin adds the Mailrith Agent Skill and focused tools that connect to one Mailrith workspace through OAuth.

1. Open the `Plugins` tab in ChatGPT or Codex and search for `Mailrith`. In Codex CLI, enter `/plugins` to open the plugin browser.
2. Select `Mailrith`, install the plugin, and start a new chat or Codex session.
3. Choose `Connect` when ChatGPT or Codex asks you to connect Mailrith.
4. Sign in to Mailrith, choose one workspace, review the requested permissions, and select `Allow Access`.
5. Begin with a read-only request, then add write access only when the task needs it. Confirm any change from the saved Mailrith resource or its progress endpoint.

> Plugins are not available in the Codex IDE extension. Use a supported ChatGPT surface, the ChatGPT desktop app for Codex, or Codex CLI to install and use the Mailrith plugin.

## Connect Mailrith To Claude

The Mailrith Connector is available in Claude's Connectors Directory. It connects through OAuth, so you do not paste a workspace API key into Claude.

1. Open Claude or Claude Desktop, then open `Customize` > `Connectors`.
2. Select the `+` button, choose `Browse connectors`, and search for `Mailrith`.
3. Choose `Mailrith`, review its capabilities, and select `Connect`.
4. Sign in to Mailrith, choose one workspace, review the requested permissions, and select `Allow Access`.
5. Begin with a read-only request. Add write tools only when the task needs them, then confirm every change from the saved Mailrith resource or its progress endpoint.

> If Mailrith does not appear or the connection is unavailable, ask your Claude organization owner whether connector access is restricted.

## 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): 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.

- [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.
