MCP · Hosted server
The marketing MCP server for your AI
Let Claude, Cursor, or any MCP client work inside your Spreeflo workspace — build segments, draft campaigns, and read your numbers without leaving the chat.
Works on every plan·Sign in, no key to paste·Nothing to self-host
claude mcp add --transport http spreeflo https://mcp.spreeflo.com/mcpWrites apply to your live workspace immediately — there's no approval queue here. Keep a human in the loop and check your client's confirmation settings first.
Why connect it
Your marketing stack, in the tool you're already thinking in
No copy-pasting CSVs into a chat window, no screenshots of dashboards. Your assistant reads the live workspace and does the work in it.
Ask in plain language
Describe the segment, the campaign, or the report you want. Your assistant translates it into the right tool calls and shows you what it did.
Reads your real data
Live audiences, contacts, tags, and performance numbers — answers come from the workspace itself, not from a stale export you pasted in.
Builds, not just advises
Segments, journeys, email and web push templates, and forms are all authorable over MCP. The output is a real draft in your workspace.
One URL, one sign-in
Add the hosted endpoint, sign in to Spreeflo and approve. Nothing to install, nothing to self-host, and no key to paste into your client.
Dangerous actions removed
Deletes, campaign and broadcast sends, and form publishes have no tool on the server — not left to whether your client remembered to ask you first.
Your client does the thinking
Spreeflo exposes deterministic tools and nothing more. The model reasoning — and whatever it costs — stays with the client you already pay for.
Setup
Connected in about a minute
One entry in your client, then sign in to Spreeflo and approve. There's no key to create or paste.
Add the server to your client
Same endpoint everywhere. Pick your client:
Claude & ChatGPT
claude.ai, Desktop app, Cowork, ChatGPT
Custom connector
- 1.Claude apps and Cowork: Settings → Connectors → Add custom connector.
- 2.ChatGPT: turn on Developer mode in Settings → Connectors → Advanced, then add a custom connector with OAuth authentication.
- 3.Paste the URL below and connect.
https://mcp.spreeflo.com/mcpCursor
Cursor and other mcp.json clients
mcp.json
- 1.Add the entry below to your MCP configuration.
- 2.In the MCP settings, use the sign-in prompt next to spreeflo.
{
"mcpServers": {
"spreeflo": {
"url": "https://mcp.spreeflo.com/mcp"
}
}
}Claude Code
Terminal
One command
- 1.Run the command below in your project.
- 2.Start Claude Code, run
/mcp, pick spreeflo and choose Authenticate.
claude mcp add --transport http spreeflo https://mcp.spreeflo.com/mcpSign in and approve
Your client opens Spreeflo in the browser. Sign in, pick the workspace to connect, and click Approve. Tick Make changes if the assistant should be able to write — leave it off for a read-only connection.
Check it works
Ask for something small — "list my Spreeflo audiences". A working connection answers with your real audience names.
Running a headless agent that can't open a browser? Give it an API key in the Authorization header instead — never in the URL.
In practice
What it looks like to actually use
Two ordinary requests, and what your assistant does with the tools behind them.
Find everyone who opened something in the last 30 days but never clicked, and draft a re-engagement email for them.
Built the segment from your open and click events, then drafted the email against it:
list_audiencescreate_segmentget_segment_previewcreate_email_template
The segment and template are real drafts in your workspace. Sending stays in the app — MCP will not start a campaign.
How did last month’s campaigns do, and which subject line worked best?
Pulled performance for every campaign in the window and compared them per template:
list_campaignsget_campaign_performancelist_link_clicks
Read-only — the numbers come straight from your workspace, so there is nothing to export or reconcile.
Coverage
Everything it can touch
The same surfaces you work with in the app, exposed as tools — and a short list that is deliberately off limits.
Audience
- Audiences and contacts
- Segments, static and dynamic
- Tags
- Custom contact attributes
- CSV import
Sending
- Campaigns and journeys
- Email templates
- Web push templates
- Sender and domain identities
Capture
- Forms and question types
- Inline and popup embeds
- Response summaries
- CSV export of responses
Insight
- Campaign and web push performance
- Tracked events and pages
- Link clicks
- Form analytics
What MCP can’t do
These are irreversible or they reach real people, so they are removed from the surface rather than left to your client's confirmation settings. A person does them in the app.
Supercharge your marketing automation
FAQ
Questions, answered.
The Model Context Protocol is an open standard for connecting AI assistants to real tools and data. Instead of pasting exports into a chat window, your assistant calls a server directly — reading your live workspace and acting in it. Spreeflo runs a hosted MCP server, so there is nothing to install or self-host.
Any client that speaks remote MCP over Streamable HTTP — ChatGPT, Claude and Claude Cowork, Claude Code, Cursor, and others. They connect by signing in: you approve the connection from your Spreeflo account and pick the workspace. Headless agents that cannot open a browser send a Spreeflo API key in the Authorization header instead. Either way they reach the same tools.
Audiences and contacts, segments and tags, campaigns and journeys, email and web push templates, forms, and reporting. Your assistant can read all of it and create or edit most of it — the same capabilities you have in the app, on the same plan gates.
It cannot delete anything or start a send. The riskiest actions are removed from the surface rather than left to your client settings: there is no tool for deletes, starting or resuming a campaign or journey, sending or scheduling a broadcast, or publishing a form. Those stay in the app, where a person does them. Journeys you have already switched on keep running, though, so editing a contact, its tags, a segment or an email template, or importing contacts, can set one off, just as the same edit would in the app.
Not on this surface — a write applies to your live workspace the moment your assistant calls it. Whether you get asked first is entirely your client’s decision, so check its confirmation settings before you start. If you want a review step, use Spreeflo’s in-app AI, which queues changes as proposals instead.
Yes. When you approve the connection, leave Make changes unticked. Your assistant can still read everything, but it is offered no tool that changes your workspace. To allow changes later, reconnect and tick it.
Your connected client does all the model reasoning, so the model cost sits with that client rather than with Spreeflo. On our side the only governor is a rolling limit of roughly 120 tool calls per minute per workspace — there is no daily quota to wait out, and the window drains continuously.