AI Agent Supported Actions And Support

Use the current supported-actions matrix, understand operation terms, account for freshness and compliance boundaries, and troubleshoot without sharing secrets or Subscriber content.

10 min read

Supported Actions

The table below uses consistent action words: Read does not change workspace data, Draft saves editable work without an external effect, Test uses a controlled recipient, Execute can affect real Subscribers or external systems, and Unsupported means Mailrith does not offer a safe agent operation for that task.

Current Support Matrix

Resource                 Read  Draft  Test  Execute  Unsupported Or Restricted
Workspace and capability Yes   No     No    No       Billing and ownership changes
Subscribers               Yes   Yes    No    Yes      Raw consent evidence and secret fields
Tags and custom fields    Yes   Yes    No    Yes      Unbounded bulk changes
Segments                  Yes   Yes    Yes   Yes      Unbounded preview or search
Broadcasts                Yes   Yes    Yes   Yes      Writes without Manage Broadcasts
Sequences                 Yes   Yes    Test  Yes      Writes without Manage Sequences
Automations               Yes   Yes    Test  Yes      Writes without Manage Automations
Forms and landing pages   Yes   Yes    Yes   Yes      Writes without each resource Permission
Email Delivery Connections Yes  Yes    Yes   Yes      Provider credentials remain browser-only
Webhooks                  Yes   Yes    No    Yes      Secret display or writes without Manage Webhooks
Analytics and diagnostics Yes   No     No    No       Raw-event scans and unbounded reports
Provider credentials      No    No     No    No       Entered only by a signed-in user in Mailrith

Execute support means the operation exists; it does not mean the connected credential may use it. Current resource permissions, workspace state, resource validation, and provider checks still apply.

Permission And Authorization Terms

A Permission controls whether a connection may run an operation. Mailrith checks that Permission on every request. Revoking the API key or Authorized App stops new access; it does not undo completed work.

Mailrith does not require separate workspace enrollment or a second per-action approval. Every operation still requires its exact Permission and passes through normal resource, preflight, provider, idempotency, and internal rollout checks.

Freshness, Compliance, And Provider Boundaries

Capability, resource, diagnostic, and progress responses describe Mailrith when the request is processed. Analytics use compact rollups and can lag live events; always read the response range and completion state.

Mailrith enforces its stored consent, suppression, unsubscribe, complaint, frequency, preflight, and provider-readiness rules. You remain responsible for lawful basis, permission to contact Subscribers, the accuracy of model-produced content, sender identity, delivery-provider terms, privacy notices, retention duties, and the laws that apply to your use.

Mailrith does not expose provider credentials to agents. An agent can start a short-lived setup link, but the signed-in user enters the credentials directly in Mailrith. After setup, verify the connection and send a real test email. Provider acceptance is not proof of inbox delivery. When an outcome is Uncertain, check Broadcast progress and provider evidence before retrying.

Support Playbooks

Start every support request with the workspace name, client name and version, approximate time, operation, target resource, and Mailrith request ID. Never send an API key, OAuth token, Subscriber export, request body, full email body, or provider credential.

Connection failure: check the exact MCP URL, OAuth return address, expiry, resource binding, and requested Permission. Reconnect or rotate only after identifying the cause.
Denied Permission: review an API key in Settings → API Keys or an OAuth app in Integrations → Authorized Apps, then remove the operation or have the owner grant a Work Profile that covers the connection's intended job.
Resource Conflict: read the current resource, adjust the intended request, and retry only if the operation is still needed.
Uncertain Execution: stop retries, inspect the target and provider progress, and share the request ID with support if the final effect cannot be reconciled.
Compromised Connection: revoke an API key in Settings → API Keys or an OAuth app in Integrations → Authorized Apps, confirm new requests fail, then create a smaller replacement credential only after review.

Verified Workflow Evidence

The quickstarts and repository examples are test recipes, not customer case studies. Mailrith has no verified customer workflow to publish yet. A case study may be added only after the customer confirms the workflow, Permissions, measured result, and wording. Until then, Mailrith must not present a hypothetical autonomous workflow as customer evidence.

Need Help Shipping an Integration?

Reach the Mailrith team if you need help planning a sync, validating a webhook flow, or troubleshooting a request.

Contact Mailrith

AI Agent Analytics And Compliance

MCP Server