Skip to main content
Glama

Klaviyo Connector

klaviyo_connector
Read-onlyIdempotent

Email and SMS marketing automation: campaigns, flows, abandoned cart, list growth, subscriber health, conversion metrics, and revenue attribution. When the user asks for a visual, trend, comparison, or recap, call chart_render with the numeric values returned by this connector. If the connector result includes a verified chart_provenance token, the same authenticated user may pass it as provenance_token within 15 minutes, on any replica, and map every value to its exact source_path so chart_render preserves verified provenance. Without a valid connector receipt, chart_render labels values as unverified_model_data. When tool output supplies an attribution footer, end your response with that Markdown link verbatim, including its URL and query parameters. Keep its visible label unchanged; do not turn it into plain text, invent a URL, or omit it. Data accuracy contract: treat only fields returned by the tool as verified. Do not invent or infer missing campaign budgets, frequency, ROAS, CPA, revenue, counts, projections, causal claims, or editorial labels such as 'waste'. Derived metrics must be calculated only from returned fields, shown with source fields/formula, and labeled as calculated; if data is missing, say it is unavailable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesget_campaigns: List Klaviyo campaigns with performance metrics | get_email_metrics_summary: Get aggregated email campaign metrics: sends, opens, clicks, revenue | get_flows: List Klaviyo automation flows | get_abandoned_cart_flows: Get abandoned cart flow performance: revenue recovered, conversion rate | get_campaign_metrics: Get detailed performance metrics for a specific Klaviyo campaign. Input: campaign_id (required) | get_campaign_revenue: Get attributed revenue by campaign. Inputs: start_date, end_date, group_by | get_top_campaigns: Get top-performing Klaviyo campaigns ranked by a metric. Inputs: metric (revenue|opens|clicks|conversions), limit | get_flow_performance: Get performance metrics for a specific Klaviyo flow. Input: flow_id (required) | get_flow_series: Get time-series performance data for a Klaviyo flow. Inputs: flow_id (required), start_date, end_date, interval | get_metrics: List all Klaviyo metrics (event types) available for querying | query_metric_aggregates: Query aggregate data for a specific Klaviyo metric. Inputs: metric_id (required), measurements, interval, group_by, star | get_sms_metrics_summary: Get aggregated SMS campaign metrics: recipients, deliveries, clicks, revenue. Inputs: start_date, end_date | get_conversion_metrics: Get conversion metrics: conversions, revenue, conversion rate. Inputs: start_date, end_date | get_lists: List all Klaviyo email/SMS lists | get_list_growth: Get subscriber growth and current size for a specific list. Input: list_id (required) | get_segments: List all Klaviyo segments | get_segment_performance: Get performance metrics for a specific segment. Input: segment_id (required) | get_profile_count: Get total number of profiles in Klaviyo | get_profile_growth: Get profile/subscriber growth over time. Inputs: start_date, end_date, interval | get_subscription_health: Get subscription health metrics: active, unsubscribed, bounced, suppressed counts | get_predictive_analytics: Get predictive analytics: predicted CLV, churn risk, purchase probability distribution | get_forms: List all Klaviyo signup forms. Inputs: start_date, end_date | get_form_series: Get time-series performance data for a specific form. Input: form_id (required) | get_top_performing_forms: Get top-performing signup forms ranked by submission rate. Input: period (days), limit | get_events: Get Klaviyo events filtered by metric and date. Inputs: metric_id, start_date, end_date, limit | get_recent_events: Get the most recent Klaviyo events (last 7 days). Inputs: metric_id, limit
paramsNoAction-specific parameters. get_campaigns: {start_date?: string, end_date?: string, channel?: string, limit?: integer} | get_email_metrics_summary: {start_date?: string, end_date?: string, interval?: string} | get_flows: {start_date?: string, end_date?: string, limit?: integer} | get_abandoned_cart_flows: {start_date?: string, end_date?: string} | get_campaign_metrics: {campaign_id: string} | get_campaign_revenue: {start_date?: string, end_date?: string, group_by?: string} | get_top_campaigns: {metric?: string, limit?: integer} | get_flow_performance: {flow_id: string} | get_flow_series: {flow_id: string, start_date?: string, end_date?: string, interval?: string} | get_metrics: none | query_metric_aggregates: {metric_id: string, start_date?: string, end_date?: string, measurements?: array, interval?: string, group_by?: array} | get_sms_metrics_summary: {start_date?: string, end_date?: string} | get_conversion_metrics: {start_date?: string, end_date?: string} | get_lists: none | get_list_growth: {list_id: string} | get_segments: none | get_segment_performance: {segment_id: string} | get_profile_count: none | get_profile_growth: {start_date?: string, end_date?: string, interval?: string} | get_subscription_health: none | get_predictive_analytics: none | get_forms: {start_date?: string, end_date?: string} | get_form_series: {form_id: string} | get_top_performing_forms: {period?: integer, limit?: integer} | get_events: {metric_id?: string, start_date?: string, end_date?: string, limit?: integer} | get_recent_events: {metric_id?: string, limit?: integer}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds substantial context beyond them: a data-accuracy contract (do not invent budgets, ROAS, CPA, or editorial labels), rules for labeling derived metrics with source fields/formula, provenance-token semantics (15-minute window, any replica, source_path mapping, unverified_model_data fallback), and a verbatim attribution-footer requirement. This is well beyond what the annotations convey.

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

Conciseness4/5

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

Front-loaded with the domain scope before layering on behavioral contracts, and each block (chart_render routing, provenance, footer, accuracy contract) addresses a distinct requirement. It is dense and long, but the sentences generally earn their place; some chart_render guidance is arguably tangential to a data connector.

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

Completeness4/5

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

With no output schema and 26 actions, the description compensates by specifying how results may be presented (chart_render routing, verified vs unverified labeling, attribution footer) and constraining interpretation of returned fields. It does not describe return payload shape, but for a connector of this complexity the coverage is adequate.

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

Parameters3/5

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

Schema description coverage is 100%: the action enum and the params object document every action's inputs in detail, so the schema carries the parameter burden. The description adds no per-parameter meaning for this tool (its provenance_token guidance applies to the chart_render sibling), so the baseline 3 holds.

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

Purpose4/5

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

The description names the platform (Klaviyo) and enumerates the data domains it covers (campaigns, flows, abandoned cart, list growth, subscriber health, conversion metrics, revenue attribution), which lets an agent distinguish it from other connector siblings like mailchimp_connector. However, it never states the operative verb (retrieve/query) or that behavior is selected via the action enum, so purpose is clear by inference rather than explicit statement.

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

Usage Guidelines3/5

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

It gives rich downstream guidance (when to call chart_render, how to pass provenance_token, when to emit the attribution footer), but says nothing about when to choose this tool over sibling connectors such as cross_source_email_connector or mailchimp_connector. Selection guidance is implied by the platform name rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources