Skip to main content
Glama
damientilman

Mailchimp MCP

create_campaign

Create a new email campaign in draft status, with support for segment targeting and A/B variate testing.

Instructions

Create a new email campaign in draft status, with optional segment targeting or A/B variate testing.

Typical workflow: create_campaign -> set_campaign_content (add HTML body) -> send_test_email (preview) -> send_campaign or schedule_campaign (deliver). The campaign is created in 'save' (draft) status and cannot be sent until content is set. Use replicate_campaign instead to clone an existing campaign.

For A/B testing, set campaign_type='variate' and pass variate_settings_json describing the test. Mailchimp will send variants to a sample of recipients, then auto-pick a winner based on winner_criteria and send it to the remaining audience after wait_time.

Authenticated via API key. Subject to Mailchimp API rate limits (max 10 concurrent requests). Respects read-only and dry-run modes.

Args: list_id: The audience/list ID to send to (e.g. 'abc123def4'). Obtain from list_audiences. subject_line: Subject line recipients see in their inbox. Keep under 150 chars. For variate campaigns testing subject lines, this is the default/fallback. title: Internal title for organizing in Mailchimp dashboard. Defaults to subject_line if omitted. preview_text: Preheader text shown after the subject line in inbox. Keep under 200 chars. from_name: Sender name on the email. Falls back to audience default if omitted. reply_to: Reply-to email address. Must be a verified domain. Falls back to audience default. segment_id: Saved segment ID to restrict recipients. Only members matching this segment receive the email. Obtain from list_segments. Omit to send to the full audience. campaign_type: 'regular' (default) for a standard campaign, or 'variate' for an A/B test. 'plaintext', 'rss', and 'absplit' (legacy A/B) are also accepted but rarely used. variate_settings_json: Required when campaign_type='variate'. JSON string with keys: winner_criteria ('opens' | 'clicks' | 'manual' | 'total_revenue'), test_size (10-100, percent of audience sampled), wait_time (minutes before picking winner), and one of subject_lines (list of 2-8 strings), from_names (list of 2-8), reply_to_addresses (list of 2-8), send_times (list of 2-8 ISO datetimes), or contents (list of 2-8 HTML strings). Example: '{"winner_criteria": "opens", "test_size": 20, "wait_time": 1440, "subject_lines": ["Spring Sale 20% off", "Last chance: 20% off Spring"]}'

Returns: JSON with fields: id (string, the new campaign ID for use with set_campaign_content, send_campaign, etc.), status ('save'), title, subject_line, web_id (int, for Mailchimp web UI link), type. Returns error if list_id is invalid, variate_settings_json is malformed, or variate settings violate Mailchimp constraints.

Example: create_campaign(list_id="abc123", subject_line="Spring Sale", preview_text="20% off") -> {"id": "def456", "status": "save", "type": "regular", ...}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
list_idYes
subject_lineYes
titleNo
preview_textNo
from_nameNo
reply_toNo
segment_idNo
campaign_typeNoregular
variate_settings_jsonNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite no annotations, the description fully explains behavior: draft status, content requirement, A/B testing mechanics, authentication via API key, rate limits, and read-only/dry-run modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, well-structured with workflow, A/B details, authentication, parameter descriptions, return info, and example. No wasted words despite comprehensiveness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers workflow, sibling alternatives, parameter semantics, return fields, error conditions, and example. Complete for a complex tool with 9 parameters and A/B testing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description provides extensive parameter details beyond schema, including usage hints, defaults, constraints, and a detailed JSON example for variate_settings_json.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it creates a new email campaign in draft status, specifying the verb 'create' and resource 'email campaign'. It distinguishes from sibling replicate_campaign for cloning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a typical workflow (create_campaign -> set_campaign_content -> send_test_email -> send/schedule), explicitly mentions when to use replicate_campaign instead, and gives context for A/B testing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/damientilman/mailchimp-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server