Spreeflo MCP server

MCP (Model Context Protocol) is an open standard for connecting AI applications to external systems. Spreeflo runs a hosted MCP server, so your own AI client — Claude, ChatGPT, Claude Code, Cursor, and other clients that support remote MCP servers — can read and build inside your Spreeflo workspace using the same tools that power Spreeflo's own AI.

You connect it once by signing in to Spreeflo from your client and approving the connection. After that, your client can look up campaign performance, inspect segments, draft emails and broadcasts, build journeys, read form responses, and keep notes on contacts — without you copying anything between tabs.

What you can do with it

Once connected, you can ask your AI client things like:

  • "What did our last three campaigns do on open and click rate?"
  • "Build me a 3-email welcome journey for the Newsletter audience and leave it in draft."
  • "Create a segment of contacts who visited /pricing twice in the last 14 days but never opened an email."
  • "Summarise the responses to our onboarding survey."
  • "Draft a web push template for the Black Friday campaign."
  • "Set up a broadcast announcing the spring sale to the Newsletter audience, and leave it as a draft for me to review."
  • "Add a note to Jane's contact record summarising what she asked for on today's call."
  • "Pause the campaign that's going out to the trial audience."

    • See the full tool catalog for everything the server offers.

    How it works

    The server is a remote MCP server served over Streamable HTTP. Your client posts to a single endpoint: 

    https://mcp.spreeflo.com/mcp

    Clients sign in with OAuth: the first time you connect, your client opens Spreeflo in your browser, you sign in, pick a workspace, and approve — read-only, or with Make changes ticked so the client can also create and edit. Headless agents that can't open a browser authenticate with a Spreeflo API key in the Authorization header instead — the same key you'd use for the Spreeflo REST API.

    The server is stateless: every request builds a fresh server, so there are no sessions to keep alive and no sticky routing to worry about.

    The safety model

    Five rules govern everything an external agent can do in your workspace:

  • Writes apply immediately. There is no approval queue on this surface. When your client calls a write tool, the change lands in the live workspace at that moment.

  • Your client controls confirmation. Spreeflo will not prompt you before a write. Every tool is annotated so a well-behaved client knows which ones only read and which ones overwrite, stop, or remove something, but it's the client that decides whether to ask you first.

  • Irreversible and outward-facing actions are not available. There is no tool for deleting anything, starting or resuming a campaign or journey, sending or scheduling a broadcast, or publishing a form — on every client, regardless of its settings. Those are only ever done by a person signed in to the Spreeflo app.

  • Your team role applies. A connection can only do what your role allows in the app, checked again on every call. A Viewer's connection is read-only; an Editor's can do everything except register sending domains and add or rename sender addresses, which need an Admin.

  • Everything is audited. Each tool call is its own agent run with an audit record, and each applied write is recorded as a change attributed to the person who approved the connection (or owns the API key). You can see exactly what an external agent did in your workspace's change history.
    • Warning: Writes over MCP apply immediately to your live workspace. Before you start, check how your AI client handles write tools — Spreeflo will not ask you to confirm.

    There's a deliberate asymmetry worth knowing: an agent can stop a send but never start one. It can pause a campaign or journey, and call off a scheduled broadcast, but not start, resume, send, or schedule anything. A broadcast it creates stays a draft until a person sends it in the app.

    Journeys you've already switched on keep running, though. Editing a contact, its tags, a segment, or an email template, or importing contacts, can enter contacts into a live journey or change what it sends — just as the same edit in the app would. Those tools are marked as destructive and say so in their descriptions, so a client that asks before destructive writes will ask you first.

    Cost and limits

    Your connected client owns all the model reasoning; Spreeflo only exposes deterministic tools. The model cost sits with that client, not with Spreeflo.

    The only governor is a rolling rate limit of about 120 tool calls per minute per workspace. There's no daily quota — the window drains continuously, so if you hit it, waiting a few seconds is enough to carry on.

    Access and scope

    A connection is scoped to one team and one person. It reaches the one workspace picked when it was approved, and every action runs as the person who approved it — with their team membership and role re-verified on every request. Remove someone from the team and their connections and keys stop working immediately; change their role and the connection follows it on the next call.

    To work in a second team, connect Spreeflo again in your client and pick that team when you approve. You can disconnect an AI app at any time from Spreeflo's settings or from the app itself. Full details are in Connect your AI client.

    Next steps

  • Connect your AI client — add the server, sign in and approve, verify the connection, and disconnect.
  • MCP tools — the full catalog, and what is not available.
  • MCP vs. the in-app AI — same engine, different surface.
    • Need Immediate Help? Contact our support team at support@spreeflo.com or check our other guides for more information.