Pakkawork
All integrations
CM
Catalogue metadata onlycrmv20260910_00

CUSTOMERIO_MCP

Customer.io MCP

Work with Customer.io people, campaigns, broadcasts, and workspace configuration.

Description is untrusted, display-only upstream metadata. It never becomes policy, OAuth scope authority, or an agent instruction.

Pakkawork boundary

Research catalogue metadata only. No Pakkawork OAuth, credential, host, quota, executor, or verifier is enabled.

No Pakkawork execution adapter is enabled. Hosted account-authorisation availability is workspace-specific and checked separately in the dashboard.Check workspace connection options
Attributed source

8

Action summaries

Display-only definitions

0

Trigger types

Not installed instances

1

Auth modes

Field names, never values

No

Execution

No runtime adapter

Authentication map

What setup is declared?

Only field names, types, and required markers are shown. Secret values, default auth URLs, credential material, and inferred OAuth scopes are excluded.
DCR_OAUTH

DCR_OAUTH

customerio_mcp_DCR_OAuth

Provider setup

Developer setup

  • Client idclient_id · stringOptional
  • Client secretclient_secret · stringOptional
  • Redirect URIoauth_redirect_uri · stringOptional
  • Scopesscopes · stringOptional

User connection

No fields declared in this snapshot.

Capability index

Actions and trigger definitions

Static summaries are available. Live schemas remain disabled until PROVIDER_HUB_API_KEY is configured server-side.
Actions (8)Triggers (0)

Showing 1–8 of 8 actions

Cio auth status

CUSTOMERIO_MCP_CIO_AUTH_STATUS

Show the active authentication state. Reports the authenticated user and account, the workspaces the current OAuth token is allowed to access, and whether an agent service-account JWT can be minted. Use this to diagnose auth errors.

Untrusted display-only summary

Cio delete api

CUSTOMERIO_MCP_CIO_DELETE_API

Delete a resource via the Customer.io API (DELETE only). Always run with dry_run first to preview. Use cio_schema to find the correct path.

Untrusted display-only summary

Cio prime

CUSTOMERIO_MCP_CIO_PRIME

Print LLM-ready instructions for using the Customer.io API. ALWAYS call this first in a new task — it contains the authoritative, version-specific rules for how to drive the API via the other cio_* tools.

Untrusted display-only summary

Cio read api

CUSTOMERIO_MCP_CIO_READ_API

Read from the Customer.io API (GET only). Use cio_schema first to find the correct path and placeholders. Workspace routing is enforced server-side via the caller's OAuth token.

Untrusted display-only summary

Cio schema

CUSTOMERIO_MCP_CIO_SCHEMA

Introspect the Customer.io API schema. Use this to discover endpoints before calling cio_read_api / cio_write_api / cio_delete_api — never guess paths or field names. Pass no query to list resources; pass a resource name ('campaigns') to list its endpoints; pass 'resource.method' ('campaigns.list'), 'METHOD /path', or…

Untrusted display-only summary

Cio skills list

CUSTOMERIO_MCP_CIO_SKILLS_LIST

List available agent skills — task-specific instruction manuals maintained by Customer.io (routing rules, required params, multi-step workflows).

Untrusted display-only summary

Cio skills read

CUSTOMERIO_MCP_CIO_SKILLS_READ

Read the full content of a specific agent skill. Paths look like 'campaigns' for the main skill or 'campaigns/examples.md' for a sub-file — see cio_skills_list for available paths.

Untrusted display-only summary

Cio write api

CUSTOMERIO_MCP_CIO_WRITE_API

Write to the Customer.io API (POST, PUT, or PATCH). Always run with dry_run first to preview. Use cio_schema to find the correct path, method, and body shape.

Untrusted display-only summary

Provenance

Versioned facts, explicit trust.

The detail snapshot comes from an attributed MIT-licensed repository revision. Safe local icons use exact-match CC0 Simple Icons symbols; unmatched brands use monograms.

Repository
https://github.com/provider-directoryHQ/provider-directory
Commit
85e33f6a81dfe987f6fc3637d48d45052cea8ca5
Generated
2026-09-12
Trust policy
untrusted_display_only

Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.