Customer.io MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Set up the connector

   Register your Customer.io MCP credentials with Scalekit so it handles the token lifecycle. You do this once per environment.

   Dashboard setup steps

   Customer.io MCP uses Dynamic Client Registration (DCR) — no client ID or secret is required. The only step is creating a connection in Scalekit and authorizing your Customer.io account.

   1. Create a connection in Scalekit

      • In the Scalekit dashboard, go to AgentKit → Connections → Create Connection.
      • Search for Customer.io MCP and click Create.
      • Note the Connection name — use this as connection_name in your code (e.g., customeriomcp).

   2. Authorize your Customer.io account

      Generate an authorization link and open it in a browser to complete the Customer.io OAuth flow.

      The user is redirected to Customer.io to sign in and grant access. Scalekit stores the token and injects it automatically into every tool call — no further configuration is needed.

      Call cio_prime first

      After connecting, call customeriomcp_cio_prime as your first tool call. It loads LLM-ready instructions about the Customer.io API structure, available resources, and recommended workflows.

4. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'customeriomcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Customer.io MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'customeriomcp_cio_auth_status',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "customeriomcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Customer.io MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="customeriomcp_cio_auth_status",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Api cio write — Write to the Customer.io API (POST, PUT, or PATCH)
• Read cio skills, cio — Read the full content of a specific Customer.io agent skill by path
• List cio skills — List available Customer.io agent skills — task-specific instruction manuals covering campaigns, segments, deliveries, analytics, and more
• Schema cio — Introspect the Customer.io API schema to discover endpoints, parameters, and response shapes
• Prime cio — Print LLM-ready instructions for using the Customer.io API
• Delete cio — Delete a resource via the Customer.io API (DELETE only)

Common workflows

Check authentication status

Use customeriomcp_cio_auth_status to verify the connection and see the authenticated user, account, and accessible workspaces.

Node.js

const status = await actions.executeTool({
  connectionName: 'customeriomcp',
  identifier: 'user_123',
  toolName: 'customeriomcp_cio_auth_status',
  toolInput: {},
});
console.log(status);

Python

status = actions.execute_tool(
    connection_name="customeriomcp",
    identifier="user_123",
    tool_name="customeriomcp_cio_auth_status",
    tool_input={},
)
print(status)

Read campaign data

Use customeriomcp_cio_read_api to fetch campaigns from a Customer.io environment. Call customeriomcp_cio_schema first to discover the correct API path and available parameters.

Node.js

const campaigns = await actions.executeTool({
  connectionName: 'customeriomcp',
  identifier: 'user_123',
  toolName: 'customeriomcp_cio_read_api',
  toolInput: {
    path: '/v1/environments/{environment_id}/campaigns',
    params: { environment_id: 'env_abc123' },
    limit: 10,
  },
});
console.log(campaigns);

Python

campaigns = actions.execute_tool(
    connection_name="customeriomcp",
    identifier="user_123",
    tool_name="customeriomcp_cio_read_api",
    tool_input={
        "path": "/v1/environments/{environment_id}/campaigns",
        "params": {"environment_id": "env_abc123"},
        "limit": 10,
    },
)
print(campaigns)

Create a campaign

Use customeriomcp_cio_write_api to create a new campaign. Always set dry_run: true first to validate the request before executing.

Node.js

// Step 1 — dry run to validate
const preview = await actions.executeTool({
  connectionName: 'customeriomcp',
  identifier: 'user_123',
  toolName: 'customeriomcp_cio_write_api',
  toolInput: {
    path: '/v1/environments/{environment_id}/campaigns',
    params: { environment_id: 'env_abc123' },
    body: { name: 'Welcome Series', type: 'triggered' },
    dry_run: true,
  },
});
console.log(preview);

// Step 2 — execute after confirming dry run looks correct
const result = await actions.executeTool({
  connectionName: 'customeriomcp',
  identifier: 'user_123',
  toolName: 'customeriomcp_cio_write_api',
  toolInput: {
    path: '/v1/environments/{environment_id}/campaigns',
    params: { environment_id: 'env_abc123' },
    body: { name: 'Welcome Series', type: 'triggered' },
  },
});
console.log(result);

Python

# Step 1 — dry run to validate
preview = actions.execute_tool(
    connection_name="customeriomcp",
    identifier="user_123",
    tool_name="customeriomcp_cio_write_api",
    tool_input={
        "path": "/v1/environments/{environment_id}/campaigns",
        "params": {"environment_id": "env_abc123"},
        "body": {"name": "Welcome Series", "type": "triggered"},
        "dry_run": True,
    },
)
print(preview)

# Step 2 — execute after confirming dry run looks correct
result = actions.execute_tool(
    connection_name="customeriomcp",
    identifier="user_123",
    tool_name="customeriomcp_cio_write_api",
    tool_input={
        "path": "/v1/environments/{environment_id}/campaigns",
        "params": {"environment_id": "env_abc123"},
        "body": {"name": "Welcome Series", "type": "triggered"},
    },
)
print(result)

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

customeriomcp_cio_auth_status # Show the active authentication state — authenticated user, account, and accessible workspaces. Call this to verify which Customer.io account is connected. 0 params ▾

Show the active authentication state — authenticated user, account, and accessible workspaces. Call this to verify which Customer.io account is connected.

customeriomcp_cio_delete_api # Delete a resource via the Customer.io API (DELETE only). Always run with dry_run=true first to preview before executing. 4 params ▾

Delete a resource via the Customer.io API (DELETE only). Always run with dry_run=true first to preview before executing.

Name Type Required Description

path string required API path including placeholders, e.g. '/v1/environments/{environment_id}/campaigns/{campaign_id}'. Placeholders are substituted from params.

dry_run boolean optional Validate and return the request without executing it.

jq string optional gojq expression to filter the response before returning.

params object optional Parameters object. Keys matching path placeholders are substituted; remaining keys become the query string.

customeriomcp_cio_prime # Print LLM-ready instructions for using the Customer.io API. Call this first in a new task to load context about available endpoints and best practices. 0 params ▾

Print LLM-ready instructions for using the Customer.io API. Call this first in a new task to load context about available endpoints and best practices.

customeriomcp_cio_read_api # Read from the Customer.io API (GET only). Use cio_schema first to find the correct path. Supports pagination, jq filtering, and dry_run preview. 7 params ▾

Read from the Customer.io API (GET only). Use cio_schema first to find the correct path. Supports pagination, jq filtering, and dry_run preview.

Name Type Required Description

path string required API path including placeholders, e.g. '/v1/environments/{environment_id}/campaigns'. Placeholders are substituted from params.

dry_run boolean optional Validate and return the request without executing it.

jq string optional gojq expression to filter the response before returning. Use to trim large responses.

limit number optional Page size.

page number optional Page number (1-indexed).

page_all boolean optional Auto-paginate and return NDJSON for the full dataset.

params object optional Parameters object. Keys matching path placeholders are substituted; remaining keys become the query string.

customeriomcp_cio_schema # Introspect the Customer.io API schema to discover endpoints, parameters, and response shapes. Use this before calling cio_read_api or cio_write_api to find the correct path and placeholders. 2 params ▾

Introspect the Customer.io API schema to discover endpoints, parameters, and response shapes. Use this before calling cio_read_api or cio_write_api to find the correct path and placeholders.

Name Type Required Description

query string optional One of: '' (list resources), 'campaigns' (resource), 'campaigns.list' (resource.method), 'GET /v1/...' (method + path), or '/v1/...' (all methods for a path).

refresh boolean optional Force re-download of API specs.

customeriomcp_cio_skills_list # List available Customer.io agent skills — task-specific instruction manuals covering campaigns, segments, deliveries, analytics, and more. 1 param ▾

List available Customer.io agent skills — task-specific instruction manuals covering campaigns, segments, deliveries, analytics, and more.

Name Type Required Description

refresh boolean optional Force re-download of skills.

customeriomcp_cio_skills_read # Read the full content of a specific Customer.io agent skill by path. Use cio_skills_list to find available paths (e.g. 'campaigns', 'fly-api/campaigns.md'). 1 param ▾

Read the full content of a specific Customer.io agent skill by path. Use cio_skills_list to find available paths (e.g. 'campaigns', 'fly-api/campaigns.md').

Name Type Required Description

path string required Skill path, e.g. 'campaigns' or 'campaigns/examples'. See cio_skills_list for available paths.

customeriomcp_cio_write_api # Write to the Customer.io API (POST, PUT, or PATCH). Always run with dry_run=true first to preview the request before executing. 6 params ▾

Write to the Customer.io API (POST, PUT, or PATCH). Always run with dry_run=true first to preview the request before executing.

Name Type Required Description

path string required API path including placeholders, e.g. '/v1/environments/{environment_id}/campaigns'. Placeholders are substituted from params.

body object optional JSON request body.

dry_run boolean optional Validate and return the request without executing it.

jq string optional gojq expression to filter the response before returning.

method string optional HTTP method: POST, PUT, or PATCH. Defaults to POST.

params object optional Parameters object. Keys matching path placeholders are substituted; remaining keys become the query string.