Provider REST API

11 actions

Connect Claude to Mailchimp

Read Mailchimp audiences, members, campaigns, reports, segments, tags and templates. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 11
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Mailchimp
Open the marketplace in your workspace, add Mailchimp to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Mailchimp shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Mailchimp asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API key, with a username in front of itRequired: Paste it in exactly that form: any word at all, then a colon, then your API key. Mailchimp reads this as HTTP Basic and ignores the username - its own documentation uses the literal word `anystring` there - but Basic authentication has no shape without one, so the colon and something before it must be present. Create the key in Mailchimp → Account & billing → Extras → API keys.; anystring:0123456789abcdef0123456789abcdef-us14
Data centreRequired: The suffix after the last dash of your API key: a key ending -us14 belongs to us14. It is also the first part of the hostname when you are signed in to Mailchimp (https://us14.admin.mailchimp.com). Every account's API lives on its own data centre, and a key sent to the wrong one is rejected as if it were invalid.; us14

What Claude can do in Mailchimp

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 10Reads
Writes: 1Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_audiences
List the account's audiences - what the Mailchimp UI calls audiences and the API calls lists. Returns each audience's ID, name, contact details, default sender and subscriber statistics. The list_id here is what every member, segment and tag action needs.
get_audience
Fetch one audience by ID, with its sender defaults, permission reminder, mandatory physical address and subscriber counts. Read stats.member_count and stats.unsubscribe_count from here rather than counting members.
list_members
List the contacts in an audience. This returns real people - email addresses, names, merge fields, signup IP addresses and location - so filter rather than paging the whole audience. Filter by status to find who is subscribed, unsubscribed, cleaned (bounced) or still pending confirmation, and by since_last_changed to see recent movement.
get_member
Fetch one contact from an audience, with their status, merge fields, tags, engagement rating and signup details. subscriber_hash is the MD5 of the lowercased email address, and Mailchimp also accepts the plain email address or a contact_id in its place.
list_campaigns
List campaigns with their type, status, audience, subject line and send time. Filter by status to separate what has gone out (sent) from what is still a draft (save) or waiting (schedule), and by since_send_time to find recent sends worth reporting on.
get_campaign
Fetch one campaign by ID, with its settings, subject line, sender, audience and recipient count. Call get_campaign_report for how it actually performed.
get_campaign_report
The reporting action. Fetch the performance of one sent campaign: emails sent, opens, clicks, bounces, unsubscribes, abuse reports, ecommerce revenue, and industry averages to compare against. Only works for a campaign that has actually been sent. Returns aggregate counts, not the individual people behind them.
list_segments
List an audience's segments, with each one's type and how many contacts it currently matches. saved segments are rule-driven and re-evaluated; static segments are fixed lists, which is also how Mailchimp stores tags internally. Returns definitions and counts, not the contacts in them.
list_tags
List the tags defined on an audience, as ID and name pairs. Pass name to keep only tags starting with that prefix; omit it for all of them. This endpoint has no paging of its own, so a very heavily tagged audience returns everything in one response.
list_templates
List the email templates available to the account - the ones your team saved (user), Mailchimp's own starting points (base) and its gallery designs (gallery). Returns names, IDs and edit dates, not the HTML.

Writes

Creates or updates something on the other side.

add_or_update_member
Add a contact to an audience, or update one already on it. Mailchimp keys on subscriber_hash, so calling this twice with the same address updates rather than duplicates. status_if_new is what a brand new contact gets and is ignored for one that already exists; status changes an existing contact. Use "pending" for status_if_new to send the double opt-in confirmation, "subscribed" to add them outright - only do that where you have a record of consent. Setting status to "unsubscribed" removes them from every future send.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches Mailchimp rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Mailchimp, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Mailchimp of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Mailchimp: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Mailchimp. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Mailchimp's own rate limits. A call that Mailchimp refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Mailchimp?

11 named actions: 10 that only read and 1 that write. They include list_audiences, get_audience and list_members. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Mailchimp connector need?

API key. The connector asks for api key, with a username in front of it and data centre. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Mailchimp connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Mailchimp connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Mailchimp rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Mailchimp, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Mailchimp of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Mailchimp. An agent has to ask. Toolspoke does not retry, queue or back off around Mailchimp's own rate limits. A call that Mailchimp refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Mailchimp's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Mailchimp?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More marketing connectors

Browse all of them