MCP - XpressBot

What is this?

MCP (Model Context Protocol) is a standard that lets AI assistants call an application’s own tools directly, instead of you copying data back and forth. This platform runs an MCP server so you can connect an assistant such as Claude, Cursor, or VS Code to your workspace: they can read your inbox and conversation history, contacts, campaigns, automations and their runs, AI agents, orders, events, activity and the product docs, and make changes after you approve them — from updating a contact or sending a template to creating campaigns, applying one change to many contacts at once, and building AI agents and automations from a description. There is nothing to install on the server — point your client at this URL with your API key.

The Developer Portal’s Reference tab has three sub-tabs, in this order: Workspace API, MCP Server, Platform API. This page documents the MCP Server tab. Connecting a client needs an API key, which needs the API Access permission (settings:api) — see Authentication.MCP is also a plan feature. The MCP Server tab only appears if MCP is enabled on your installation; if your plan doesn’t include it, the tab shows an Upgrade badge and connections are refused until you upgrade.

[SCREENSHOT: mcp-reference-tab — The Developer Portal’s Reference tab with Workspace API, MCP, and Platform API sub-tabs, MCP selected]

Server URL

https://YOUR_DOMAIN/api/mcp


Transport	Streamable HTTP
Server name	`workspace` (the platform is white-labelled, so no brand name is sent to MCP clients)
Auth	API key, as an `Authorization: Bearer` header
Scope	One channel per connection, via the `X-Channel-Id` header (or `?channelId=` for clients that can’t set custom headers)

What can I do here?

Connect any MCP client that supports remote HTTP servers with custom headers
Give the assistant read access to your inbox, conversations, contacts, labels, custom fields, pipelines, automations and their runs, campaigns, templates, AI agents, orders, catalog, events, connected networks, and the product docs
Let it make approved changes: add a note, update a contact, set a custom field, add or remove a label, move a pipeline stage, send a template, close a conversation, hand off to a human, or trigger an automation
Have it create labels, custom fields, and pipelines (and add pipeline stages), and apply one change to many contacts or conversations at once with a background job you can check
Have it write a WhatsApp template draft, create a campaign from an approved template, or send a free-form utility or authentication message with Direct Send
Have it build a WhatsApp Flow (an in-chat form) from a description, saved as a draft you review and publish in Flows
Have it build an AI agent from a description — instructions, knowledge, skills, capabilities, and human handoff — check that it is ready, and publish it
Have it build an automation from a description, saved as an inactive draft, then replace the draft’s flow, activate it, or pause it
See the exact same tool list this page documents live in-app, under Developer → Reference → MCP — see the full tool catalog

How to use it

Get your connection details

API key — Generate a key in API Keys (in the Developer Portal). The assistant acts as you, with your permissions. Needs the API Access permission.Channel — Each connection works inside one channel. Find your channel IDs with List channels, or pick one in the Developer Portal’s MCP tab, which fills it into the setup snippets for you.

Connect your client

Pick your client and copy the snippet, replacing <API_KEY> and <CHANNEL_ID> with your own values.

Claude Code
Claude Desktop
Cursor
VS Code
Other

Run this in your terminal, then run /mcp inside Claude Code to check the connection.

claude mcp add --transport http workspace https://YOUR_DOMAIN/api/mcp \
  --header "Authorization: Bearer <API_KEY>" \
  --header "X-Channel-Id: <CHANNEL_ID>"

Settings → Developer → Edit Config, add this to claude_desktop_config.json and restart Claude. Needs Node.js installed.

{
  "mcpServers": {
    "workspace": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://YOUR_DOMAIN/api/mcp",
        "--header",
        "Authorization:${AUTH}",
        "--header",
        "X-Channel-Id:${CHANNEL}"
      ],
      "env": {
        "AUTH": "Bearer <API_KEY>",
        "CHANNEL": "<CHANNEL_ID>"
      }
    }
  }
}

Add this to ~/.cursor/mcp.json (or .cursor/mcp.json in a project) and enable the server in Cursor settings.

{
  "mcpServers": {
    "workspace": {
      "url": "https://YOUR_DOMAIN/api/mcp",
      "headers": {
        "Authorization": "Bearer <API_KEY>",
        "X-Channel-Id": "<CHANNEL_ID>"
      }
    }
  }
}

Add this to .vscode/mcp.json in your project, then start the server from the MCP view.

{
  "servers": {
    "workspace": {
      "type": "http",
      "url": "https://YOUR_DOMAIN/api/mcp",
      "headers": {
        "Authorization": "Bearer <API_KEY>",
        "X-Channel-Id": "<CHANNEL_ID>"
      }
    }
  }
}

Any MCP client that supports remote HTTP servers with custom headers can connect with these values.

URL:        https://YOUR_DOMAIN/api/mcp
Transport:  Streamable HTTP
Header:     Authorization: Bearer <API_KEY>
Header:     X-Channel-Id: <CHANNEL_ID>

Replace <API_KEY> with your key. Keep the key out of shared files and repositories.

Claude on the web (claude.ai connectors) is not supported yet: it only signs in with OAuth, and this server uses API keys. Use Claude Code or Claude Desktop.

Ask your assistant

Once connected, just ask in plain language. For example:

“Find the contact named John and show his labels.”
“Which events next week still have seats?”
“Tag everyone who asked about pricing today with the Lead label.”
“Build an AI agent for order support from this description, then check that it is ready to publish.”
“Build a welcome automation for new conversations that asks for the customer’s name and tags them as a lead, then turn it on.”

Available tools

What the assistant can use. Your key only sees the tools your permissions allow in the selected channel. See the full tool catalog for every tool, grouped by area, with its description, mode, and required permission.

How it stays safe

Your client asks you to approve every change before it runs.
Nothing can be deleted or cancelled over MCP. Those actions stay in the dashboard.
The assistant has exactly your permissions, checked again on every call.
Every call stays inside the channel you connected. Other channels are never visible.
The same rate limits as the Workspace API apply, with stricter limits for sending messages and starting automations. Creating a campaign counts as sending messages.
Tools that reach customers — sending a template or Direct Send message, creating a campaign, activating an automation, publishing an AI agent — are marked Reaches customers in the Developer Portal. New AI agents and automations are always created inactive, so nothing goes live until you explicitly publish or activate it.

Troubleshooting / Technical Notes

Code	What it means
`400`	Missing channel. Send the `X-Channel-Id` header (or `?channelId=`).
`401`	Missing or invalid API key. Check the `Authorization` header.
`403`	The key’s owner does not have the API Access permission, or MCP is not included in your plan (or not enabled on your installation).
`404`	The channel does not exist or you cannot access it.
`429`	Too many requests. Wait a minute and try again.

400 in detail. The response is {"error": "channel_required", "message": "Send the channel to work in as the X-Channel-Id header (or ?channelId=). List yours with /api/workspace/v1/channels/list."}. Add the header or query parameter shown in the connection snippets above.
403 with “MCP not included in your plan”. The key’s owner is on a plan without the MCP feature. Upgrade the plan, or ask your platform administrator to include MCP in it — plan features are edited on the user’s Features tab under Platform Users.
404 instead of 403 for a channel you can’t access. This is deliberate: the server always returns 404 for a channel id it can’t resolve for your key, whether it doesn’t exist or you simply don’t have access to it, so channel ids can never be probed or leaked.
A tool doesn’t show up, or a call fails with a permission error. The MCP server only ever offers tools your API key’s owner has permission to use, re-checked on every call — grant the underlying permission (see each tool’s “Permission needed” in the tool catalog), not the API Access permission again.
A write never seems to happen. Every write tool needs your MCP client’s own approval step (Claude Code, Claude Desktop, Cursor, and VS Code all prompt you before running a tool call) — check your client isn’t waiting on an approval dialog.
Nothing about deleting or cancelling. By design: destructive actions (like cancelling a registration) are never exposed over MCP and stay dashboard-only.

​What is this?

​Server URL

​What can I do here?

​How to use it

​Available tools

​How it stays safe

​Troubleshooting / Technical Notes

​Related docs

What is this?

Server URL

What can I do here?

How to use it

Available tools

How it stays safe

Troubleshooting / Technical Notes

Related docs