MCP server — ReplyPlex developer docs

Connect Claude, ChatGPT, or your IDE to your ReplyPlex workspace over the Model Context Protocol.

ReplyPlex speaks the Model Context Protocol — the open standard AI apps use to work with external systems. Connect your workspace once, and your assistant can search tickets, pull customer history, look things up in your knowledge base, and (with permission) triage conversations.

https://api.replyplex.com/mcp

Connect by signing in (recommended)

Pick your app. Chat apps (Claude, ChatGPT) connect by pasting the URL above; agentic ones (Claude Code, Cursor) can set themselves up from a pasted prompt — a conversation is deliberately not allowed to grant itself new tool servers, which is why the two differ.

These menus move around. If the steps below don’t match your build, what you’re looking for is anywhere the app lets you add a remote (Streamable HTTP) MCP server — point it at the URL above and it will work.

claude.ai (or the desktop/mobile app) → Settings → Connectors → Add custom connector.
Paste https://api.replyplex.com/mcp — leave OAuth fields and headers empty — then Add → Connect.
Sign in to ReplyPlex in the browser sheet, pick your workspace, Approve.
In a chat: + → Connectors → enable ReplyPlex, then try the prompt below.

First prompt to try

Using ReplyPlex, show me what needs my attention: list my inboxes, then find the
conversations assigned to me that are still active, oldest first. For each, tell me what the
customer is waiting on and what you'd suggest doing next.

Settings → Plugins → MCPs → Add server ("Connect to a custom MCP").
Name it ReplyPlex, then switch Type from STDIO to Streamable HTTP — STDIO is the default and is for local processes, not a hosted server.
Paste https://api.replyplex.com/mcp as the URL → Save.
Connect / authenticate → sign in to ReplyPlex → Approve. (Older builds keep this under Settings → Connectors, behind developer mode.)
The desktop app introduces itself as Codex on the consent screen, and shows as Unverified because it registered itself — both expected. Check that Sends to is your own machine (127.0.0.1) before approving.

First prompt to try

Using ReplyPlex, summarise the last 24 hours in my support workspace: what came in,
what's still open, and anything that looks urgent or has a bad CSAT rating.

Paste the prompt below into Claude Code — it registers the server itself.
Or run it yourself: claude mcp add --scope user --transport http replyplex https://api.replyplex.com/mcp
Then /mcp → replyplex → authenticate, and approve in the browser.

Self-setup prompt

Set up the ReplyPlex MCP server for me, then verify it works.

ReplyPlex is my team's email support platform (tickets, customers, knowledge base).
No API key: authentication is a browser sign-in that I'll complete myself.

1. Register it in your own MCP config:
 claude mcp add --scope user --transport http replyplex https://api.replyplex.com/mcp
2. Trigger authentication for the new server. A browser will open a ReplyPlex sign-in —
 pause and let me approve it.
3. Once I've approved, verify by calling the list_inboxes tool and showing me my inboxes.

Never ask me for a password or token in chat; the browser sign-in is the only credential step.

Paste the prompt below into Cursor — it writes its own MCP config.
Or: Settings → MCP & Integrations → New MCP server.
Authenticate when prompted and approve in the browser.

Self-setup prompt

Set up the ReplyPlex MCP server for me, then verify it works.

ReplyPlex is my team's email support platform (tickets, customers, knowledge base).
No API key: authentication is a browser sign-in that I'll complete myself.

1. Add this to ~/.cursor/mcp.json under "mcpServers":
 "replyplex": { "url": "https://api.replyplex.com/mcp" }
2. Trigger authentication for the new server. A browser will open a ReplyPlex sign-in —
 pause and let me approve it.
3. Once I've approved, verify by calling the list_inboxes tool and showing me my inboxes.

Never ask me for a password or token in chat; the browser sign-in is the only credential step.

For any other MCP-capable app, add the URL above as a remote/HTTP MCP server.
The prompt below works in any agent that can edit its own MCP configuration.

Generic self-setup prompt

Set up the ReplyPlex MCP server for me, then verify it works.

ReplyPlex is my team's email support platform (tickets, customers, knowledge base).
MCP endpoint: https://api.replyplex.com/mcp — Streamable HTTP, standard MCP OAuth.
No API key: authentication is a browser sign-in that I'll complete myself.

1. Register the server in YOUR OWN MCP configuration, using this environment's native
 mechanism (a remote/HTTP MCP server entry named "replyplex").
2. Trigger authentication for the new server. A browser will open a ReplyPlex sign-in —
 pause and let me approve it.
3. Once I've approved, verify by calling the list_inboxes tool and showing me my inboxes.

Never ask me for a password or token in chat; the browser sign-in is the only credential step.

If you can't modify your own MCP configuration here (e.g. a chat app like claude.ai or
ChatGPT), don't work around it — tell me the exact steps for THIS app instead.

On first use the app opens a ReplyPlex sign-in: log in with your normal account, pick a workspace if you belong to several, and approve. The connection acts as you — your inboxes, your permissions — and assignee:me style questions work.

Workspace admins see every connection under Settings → Developer → Connected AI apps (who connected what, acting as whom, last used) and can revoke any of them; revocation is immediate.

Connect with an API key

For scripts, CI, or clients that send fixed headers, an API key works instead: send Authorization: Bearer rp_live_… on every request. A key acts org-wide rather than as a person, so prefer signing in for interactive use.

Scopes

Scope	Allows
`read`	Search and read conversations, customers, knowledge, and reference data.
`write`	Everything in `read`, plus triage: internal notes, tags, assignment, status, priority, custom fields.

The scope is fixed when the connection is approved and shown on the consent screen. Read-only connections don’t even see the write tools.

Tools

Read (all connections):

Tool	What it does
`search_conversations`	Full-text search with `status:` / `assignee:` / `tag:` operators, optionally scoped to one inbox. Returns a page of matches plus `total`, the real match count.
`list_conversations`	Page through an inbox, filterable by status and `updated_after`.
`get_conversation`	The full thread — messages, notes, activity, CSAT, custom fields.
`search_customers`	Find customers by name or email.
`search_knowledge`	Semantic search over your docs, curated Q&A, and past answers.
`get_workspace_report`	Volume, backlog, response times, CSAT, and per-agent replies over 1–90 days.
`list_inboxes` · `list_tags` · `list_team_members` · `list_saved_replies` · `list_custom_fields`	Reference data.

Triage (write scope only):

Tool	What it does
`add_note`	Internal note (never emailed), with optional @mentions.
`apply_tag` / `remove_tag`	Tag management.
`assign_conversation`	Assign or unassign a teammate.
`set_status`	Close, reopen, or snooze until a time.
`set_priority`	LOW / NORMAL / HIGH / URGENT, or clear.
`create_draft`	Save a reply draft for you to review and send in the console — it is never sent by the AI.
`set_custom_field`	Set or clear one custom-field value.

Every triage action lands in the conversation’s activity timeline attributed to the person whose connection performed it — e.g. Rupok · via Claude — so nothing an AI app does is anonymous or irreversible.

Prompts and resources

In clients that surface them, the server also publishes three ready-made prompts — Triage my queue, Daily digest, and Brief me on a customer — and a resource template (replyplex://conversations/{id}) for attaching a ticket as context directly.

Rate limits

300 requests per 60 seconds per connection, in a separate bucket from the REST API.