Connected AIs lets an AI assistant you already use, such as ChatGPT or Claude, work with your ReplyZen workspace through the Model Context Protocol (MCP). You can ask it how your agents are set up, what happened to a comment, or why an automation did or did not fire. If you allow it, it can also preview and apply a small set of configuration changes.
The dashboard stays your home for ReplyZen. MCP is a conversational way to inspect the same workspace.
MCP is in private beta for existing ReplyZen customers. ReplyZen turns it on per workspace; owners can't switch it on themselves.
ReplyZen MCP supports the assistants below. Setup steps and available actions can change during the private beta.
| Assistant | Status |
|---|---|
| ChatGPT | Beta |
| Claude | Beta |
| Codex | Early |
| Claude Code | Beta |
| Other MCP clients | Not yet verified |
Every assistant uses the same MCP address:
https://queues.replyzen.ai/mcp/
Works in ChatGPT on the web. On Pro, ChatGPT can read your workspace. On Business, Enterprise, and Edu it can also make changes, if your workspace admin allows custom apps.
See the official ChatGPT setup guide for current instructions. See also plan and workspace requirements.
Works on every Claude plan. Free allows one custom connector. On Team and Enterprise, an owner adds ReplyZen once, then each member connects it.
See the official Claude setup guide for current instructions.
codex mcp add replyzen --url https://queues.replyzen.ai/mcp/
codex mcp login replyzen
The login command opens ReplyZen in your browser for workspace approval. On a machine without a browser, run codex mcp login replyzen --no-browser, open the printed URL on another device, and paste the full redirect URL back into the terminal.
See the official Codex setup guide.
claude mcp add --transport http --scope user replyzen https://queues.replyzen.ai/mcp/
The --scope user option makes ReplyZen available in every project. Then open Claude Code and run /mcp to review the server and authenticate, or run claude mcp login replyzen from your shell.
See the official Claude Code setup guide.
Clients that support Streamable HTTP and OAuth Authorization Code with S256 PKCE can try the same address. We haven't verified any other client yet.
A good first prompt: "Use ReplyZen to list our active agents and show which pages are assigned to each one."
When you connect, ReplyZen shows a permission screen. You pick one workspace and choose what the assistant can do there. ReplyZen identifies ChatGPT and Claude clients when their metadata is fetched from a recognized official HTTPS address. Other clients appear as custom clients; their names alone do not prove who built them. Requested permission groups are selected by default, so untick any change permissions you do not want. Check that the return address shown on the permission screen matches the assistant you started from.
| Permission | What it allows |
|---|---|
| See your ReplyZen setup (always on) | Agents and their instructions, automations, pages, and change history. It also includes the text of comments and DM conversations the assistant looks up when it lists comments or explains what happened. |
| Change agent settings | Tone, moderation, links, and other agent settings, and adding to or replacing an agent's instructions. This changes how future comments and DMs are answered. |
| Change automations | Editing triggers and scope, and turning automations on or off. An active automation can send DMs and publish replies to real people. |
| Assign pages to agents | Moving pages between agents or taking a page away from all of them. Assigning can start replies, moderation, and DMs on that page; unassigning stops replies and moderation there. |
Publishing controls (auto-publish, publish mode, confidence threshold), comment deletion, and creating or deleting agents and automations are not available over MCP. Use the dashboard for those.
These are the tools ReplyZen offers. An assistant only sees the ones its permissions allow.
Read (always available)
whoami)list_agents, get_agent)list_pages)list_comments)explain_comment)get_usage)list_automations, get_automation)list_conversations)explain_conversation)explain_automations)get_agent_changes, get_automation_changes)get_writing_guide)Change (only with the matching permission)
update_agent_settings, update_agent_instructions)update_automation, update_automation_scope)assign_pages, unassign_pages)revert_agent_change, revert_automation_change)Every change happens in two steps:
ReplyZen tells your assistant to show you the preview before it confirms. Whether it actually stops to ask you depends on your assistant's tool-approval settings. If your assistant is set to run tools without asking, it can preview and confirm in one turn. Keep approval prompts on for ReplyZen if you want to OK every change yourself, or connect with read-only access.
Every change is recorded with who made it. Agent and automation configuration changes can be reverted from the audit trail, as long as nothing else has edited that agent or automation since. A page unassignment can be put back by assigning the page again.
Revert restores configuration only. It cannot:
Open Settings → Connected AIs in your workspace.
If MCP is turned off for your workspace, existing connections stop working but still appear in Connected AIs, so members can revoke their own connections and owners can revoke any connection before MCP is turned back on.
Tell us what you want your assistant to do next from the support chat in your ReplyZen dashboard, or email [email protected]. Your assistant can't send feedback to ReplyZen for you.