MailSequence MCP

Give an AI client the tools it needs with scoped access.

A MailSequence MCP connection is bound to one workspace and an approved scope set. Its tools delegate to the same public API, so tenant isolation, validation, rate limits, idempotency, and suppression remain in force.

Reviewed September 8, 202610 minute readProduct behavior checked against current implementation
MCP uses the same public contract and authorization rules as other clients. Approve the smallest scope, inspect the advertised tools, and require human confirmation before consequential writes.

Current connection model

ElementCurrent behavior
Endpointhttps://app.mailsequence.com/api/mcp
TransportStateless HTTP JSON-RPC request and response; no streaming
ProtocolMCP protocol version 2025-06-18
IdentityOne active workspace selected during the consent flow
AuthorizationApproved workspace scopes; provisioning keys are refused
Rate limitThe same per-key limit and Retry-After behavior as the API

1. Create a scoped connection

Begin the MailSequence consent flow from a supported MCP client or connection link while signed in to the intended workspace. Review the client label, connection name, and requested scopes. Only workspace owners and admins can approve the connection.

The callback returns the connection details, endpoint, and bearer token once. Save the token in the client's secure credential store. The consent link is temporary and single-use. It does not provide general OAuth client registration or refresh tokens.

2. Understand the tool surface

ScopeAvailable tools
contacts:readlist_contacts, get_contact
contacts:writecreate_contact, update_contact
sequences:readlist_sequences
campaigns:readlist_campaigns
enrollments:writeenroll_contact
imports:writeimport_contacts

The server filters tools/list to the connection's scopes and checks authorization again when a tool is called. MCP currently exposes eight tools. The wider REST API remains separate.

3. Use a reviewable agent workflow

  1. Ask the client to list campaigns or contacts before selecting IDs.
  2. Require it to summarize the proposed audience, destination, and conflict policy.
  3. Review a small import or contact update before authorizing broader work.
  4. Require explicit confirmation before enroll_contact.
  5. Record returned IDs and batch handles so the operation can be reconciled.

Tool descriptions do not replace operator intent. An agent with write scope can perform the corresponding write, so put confirmation and source-data review in the client workflow.

4. Preserve API safety rules

  • Contact creation still deduplicates inside the workspace and never un-suppresses.
  • Import still enforces field, batch, conflict-policy, and plan-cap rules.
  • Enrollment still checks contact, campaign, state, and tenant boundaries.
  • Mutating calls can forward an idempotency key for safe retries.
  • A tool cannot call a resource outside its approved scopes.

5. Revoke access when the client no longer needs it

The current product does not provide a dedicated UI for listing and revoking MCP connections. The practical kill switch is to revoke the backing workspace API key from the Developer tab. That invalidates both MCP and REST use of the token.

Do not paste an MCP token into prompts, documentation, logs, or shared configuration. It is a bearer credential shown once and should be treated like an API key.

Sources and product basis

Connect an agent through scoped access.

Approve the minimum workspace scopes, review consequential writes, and revoke the backing key when the connection is no longer needed.