Skip to main content
Glama
Sign In

Klaviyo MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted Klaviyo MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/klaviyo-mcp-server
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data are near-identical twins: both are labeled "Step 3 (FINAL) of workflow" and repeat the same two-step prerequisite verbatim, differing only by 'execute' vs 'query'. An agent has little basis for choosing between them, while prompts_menu and query_contexts are reasonably distinct.

Naming Consistency3/5

Three names follow a verb_noun pattern (execute_action, query_contexts, query_data), but prompts_menu is noun_noun and inconsistent with the rest. query_data vs query_contexts also differ only by noun in a way that doesn't signal a meaningful distinction.

Tool Count3/5

Four tools is thin for a Klaviyo surface, but the design is intentionally a meta-gateway that funnels all resource operations through one generic action executor, so the small count is defensible. The bundling of prompts browsing alongside a generic action pipeline feels somewhat arbitrary.

Completeness3/5

A generic execute_action plus query_data can theoretically cover Klaviyo's breadth via the actions catalog, but the surface offers no prompt creation/update, no result pagination or error recovery, and forces a rigid two-call discovery ritual before any real operation. Coverage depends entirely on an opaque runtime 'available_actions' list rather than a legible tool surface.

Available Tools

4 tools
execute_actionKlaviyo Execute ActionA
Destructive
Inspect

Execute Klaviyo action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before executing.

Rely on info from steps 1-2 to construct the action body. Follow the schema exactly.

Inputs: body (required). Returns: object

prompts_menuKlaviyo PromptsA
Read-only
Inspect

Browse the Klaviyo prompt catalog.

  1. request='menu' – List public/system prompts (optionally pass workspace_id + prompt_type).

  2. request='prompt_details' – Fetch prompt body by prompt_id. Set is_custom=True + workspace_id for workspace prompts.

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsKlaviyo Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe Klaviyo data queries.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, other source metadata, AND available_actions (all tables you can query).

Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, time ranges, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object

query_dataKlaviyo Data QueryA
Read-only
Inspect

Query Klaviyo data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before querying.

Rely on info from steps 1-2 to construct the query body. Follow the schema exactly.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • GTM MCP Server

      dylanottinger
      A
      license
      Not graded
      quality
      D
      maintenance
      A unified MCP server that connects HubSpot, Clay, Apollo, Slack, and email to enable AI agents to execute multi-step GTM workflows such as prospecting, enrichment, CRM updates, and notifications.
      18 npm
      MIT

    • Ask AI

      charlesemarsh
      F
      license
      Not graded
      quality
      D
      maintenance
      Hosted MCP server connecting Shopify, Klaviyo, GA4, Meta Ads, Google Ads, Xero, Gorgias and 20+ e-commerce data sources so AI assistants can answer merchant questions that span every source at once.
      -

    • MCP-manychat

      vdloureiro
      F
      license
      A
      quality
      D
      maintenance
      MCP server for ManyChat API integration that enables Claude and other AI assistants to manage subscribers, tags, custom fields, flows, and send messages through natural language.
      17
      -

    • datavessel

      djr4
      F
      license
      Not graded
      quality
      D
      maintenance
      Hosted MCP server that gives AI agents read and write access to your full marketing & ecommerce stack — Google Analytics, Search Console, Google & Meta Ads, Shopify, WooCommerce, Shopware, Slack and LinkedIn. 100+ tools across 10 connectors. BYOK, OAuth 2.1.
      -
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources