Tool reference
Every tool a connected assistant can call, grouped the same way the server registers them. A tool is only ever offered to the assistant if your connection holds the scope it needs — there's no such thing as a write tool that's present but always errors; if you didn't grant contacts:write, the assistant simply doesn't see upsert_contacts at all. See Scopes & permissions for what each scope means.
Destructive in the tables below is the same MCP annotation Claude's own review process requires — it marks a tool whose effect can't be trivially undone (deleting a project, overwriting a tree, removing a contact), not "dangerous" in some vaguer sense. Every write tool still only takes the fields you'd expect; none of them accept a raw payload the model could smuggle arbitrary changes through.
Discovery
| Tool | Scope | Notes |
|---|
search | any of projects:read / templates:read / contacts:read | Searches projects, templates and contact lists by name. Returns opaque ids for fetch. This is the tool a deep-research-capable client calls automatically. |
fetch | same as search | Resolves one id from search into its full content. |
Email design
| Tool | Scope | Destructive | Notes |
|---|
list_projects | projects:read | | Id, name, purpose for every project. |
get_email | projects:read | | A project's preheader, current block tree, theme and response settings. |
preview_email | projects:read | | Renders through the real mailed-HTML pipeline — the exact document a send would produce. Widget-attached (see below). |
list_block_types | projects:read | | The full 44-block catalog, generated from the live registry — always current, never hand-maintained. |
list_templates | projects:read | | Your saved templates, or the approved community gallery. |
create_project | projects:write | | Optionally seeded from a built-in purpose template, with an optional preheader. |
add_block / update_block / move_block | projects:write | | Tree edits, canPlace/field-validated the same way Mia AI's edits are. |
remove_block | projects:write | ✓ | Deletes a block and its children. |
set_theme | projects:write | | Brand colors, font, type scale, button styles, link style, block spacing, card layout and dark mode. |
rename_project | projects:write | | |
delete_project | projects:write | ✓ | Permanent. |
apply_template | projects:write | ✓ | Overwrites the project's entire tree and theme. |
save_as_template | templates:write | | Snapshots the current project into a reusable template. |
publish_landing_page | projects:write | | Publishes an email as a public web page at /lp/<slug> and returns its URL. The assistant is told to show you the email and get your approval first, as with sending. |
unpublish_landing_page | projects:write | | Takes the page down. The address stays reserved for you. |
set_response_settings | projects:write | | Sets which answers make a complete response: every counted block or any answer, which blocks count, the final message and an optional https redirect. |
Audience
| Tool | Scope | Destructive | Notes |
|---|
list_data_sources | contacts:read | | Every data source, contact lists included. Credential values are never returned. |
list_contact_lists | contacts:read | | Contact lists specifically — id, name, fields, row count. |
get_contact_list_summary | contacts:read | | Counts, suppression totals and the email verification breakdown, plus the last re-check's status — no individual contact data. |
find_contacts | contacts:read | | Bounded lookup (≤25 rows, cursor-paginated). sortBy: "engagementScore" returns the list's warmest contacts first, with their score and this week's change. Every call is written to the personal-data access log, same as a dashboard contact read. |
upsert_contacts | contacts:write | | Add or update rows; enforces your plan's contact cap. |
remove_contact | contacts:write | ✓ | Permanently removes one row. |
add_suppression / remove_suppression | contacts:write | | Blocks or unblocks an address account-wide, same effect as a recipient's own unsubscribe link. |
Results
| Tool | Scope | Destructive | Notes |
|---|
get_campaign_results | analytics:read | | Opens/clicks/responses/revenue, A/B variant comparison, click heatmap. Summarized only — never raw per-recipient events. Widget-attached. |
get_email_insights | analytics:read | | One Insights view (overview, blocks, one block, audience, crosstab, sends or engagement) as aggregates, under optional date, send, variant and list filters. The same numbers as the page; audience and crosstab need Pro or above. Differences are observed, not tested. |
get_form_responses | analytics:read | | Per-question rollups; free-text answers are a capped, fenced sample. |
list_orders | analytics:read | | Product-block checkout orders. |
list_campaign_sends | analytics:read | | Past bulk sends, most recent first. |
list_schedules | analytics:read | | Recurring sends configured on a project. |
mark_order_fulfilled | commerce:write | | Marks a physical order shipped and emails the buyer. |
create_schedule | campaigns:send | | Configures a new recurring send. |
set_schedule_enabled | campaigns:send | ✓ | Marked destructive because disabling a live schedule stops future sends silently. |
Sending
| Tool | Scope | Destructive | Notes |
|---|
send_test_email | campaigns:read | | A single [Test]-prefixed copy to one address you specify — doesn't touch your real audience or need campaigns:send. |
prepare_send | campaigns:send | | Read-only by annotation — resolves the audience and renders a preview, sends nothing. Returns a confirmationToken, and how many contacts will be skipped as invalid addresses or for no consent. Widget-attached (send-confirmation card). |
confirm_send | campaigns:send | ✓ | Requires the exact confirmationToken prepare_send returned, unchanged, within 10 minutes. See Security for why. |
Mailbox & tickets
| Tool | Scope | Notes |
|---|
list_mailbox_threads / get_mailbox_thread | mailbox:read | Inbound mail at your verified domain. Message bodies are fenced as untrusted, recipient-authored content. |
reply_to_mailbox_thread | mailbox:write | Sends from the exact mailbox address the original mail arrived at, correctly threaded. |
list_tickets / get_ticket | mailbox:read | Support-ticket conversations. Same untrusted-content fencing. |
reply_to_ticket | mailbox:write | Adds an owner message and emails the recipient a link back. |
Journeys & segments
| Tool | Scope | Destructive | Notes |
|---|
list_journeys | journeys:read | | Id, name, on/off, trigger kind and step count for every journey. |
get_journey | journeys:read | | A journey's full flow, with your emails', lists' and segments' names, plus anything that would stop it from running. For a journey that's off and can run, also returns an enableToken. |
list_segments | journeys:read | | Saved segments, with their contact list and rules. |
create_segment | journeys:write | | Saves a segment on one contact list. Enforces your plan's segment cap. |
build_journey | journeys:write | | Builds a new journey, or edits one that's off, from a plain-language request, using the journey builder's Mia AI. Uses one Mia AI turn. The result is always saved turned off, and a journey that's on is never changed. |
set_journey_enabled | journeys:write (+ campaigns:send to turn on) | ✓ | Turning a journey on requires the enableToken from get_journey, unchanged, within 10 minutes and before any further edit. Same two-step idea as prepare_send/confirm_send. Pausing needs neither. |
Experiments
| Tool | Scope | Destructive | Notes |
|---|
list_experiments | analytics:read | | Your A/B experiments, newest first, both send and journey ones: status, arms, metrics, the analysis engine's latest result, any recorded decision and a link to the results page. Filters by status, kind, email or journey. |
get_experiment_results | analytics:read | | One experiment's report, the same as the results page's JSON export, plus the engine's outcome as one line. The assistant is told that line is the only verdict, so it names a winner only when the engine did. |
create_experiment_draft | projects:write | | Creates a draft send experiment on one email: name, hypothesis, metrics, and up to your plan's number of arms, split evenly. It sends nothing. You set the audience, lock and launch it in the dashboard, from the link it returns. Journey experiments are created from a split step instead. |
No tool locks, launches, decides or deploys an experiment. Those stay your own steps in the dashboard.
Account
| Tool | Scope | Notes |
|---|
get_plan_usage | none — always available | Plan, quotas, and this month's usage. Read-only, and not sensitive account data the way projects/contacts/mailbox are, so it's available regardless of which scopes you granted. |
Three tools attach an interactive widget on hosts that support MCP Apps (Claude — Gemini has no widget layer and always gets the plain-text/JSON result instead): preview_email (live desktop/mobile email preview), get_campaign_results (results dashboard), and prepare_send (the send-confirmation card, whose own Confirm & Send button is what actually calls confirm_send).