Guides

Optimove MCP Connector

📘

Version 1.0 (MVP) · May 2026. API and integration reference for the Optimove Model Context Protocol (MCP) connector. For the marketer-facing setup guide, see Optimove Academy.

🔐

Closed Beta: This capability is currently in Closed Beta and may not be available to all customers. For information beyond this article, please reach out to your Customer Success Manager.

Optimove MCP is a hosted, OAuth-secured Model Context Protocol server that connects an MCP-compatible AI client directly to your Optimove tenant. It exposes campaigns, promotions, triggers, journeys, segments, and platform-health signals as queryable surfaces, plus a constrained set of draft-creating safe-write tools. This page is the technical reference: transport, safety contracts, the full tool catalog, authentication, and operational limits.

MCP server endpoint

The connector is hosted at https://mcp.optimove.net/mcp.

The endpoint is hosted, HTTPS-only, and uses Streamable HTTP transport. There is nothing to install locally — clients connect to the remote server directly.

Connecting from Cursor, VS Code, and other MCP clients

Add a remote MCP server entry pointing to https://mcp.optimove.net/mcp with OAuth authentication. The exact configuration path varies by client; consult your client's documentation for its connector or MCP-server settings.

The full machine-readable tool manifest is published at the server endpoint and is surfaced automatically by the host client once connected.

Safety model

The connector is built around two contracts: read-only by default, and safe-write where the action is reversible and non-destructive.

Read-only tools

All inspection, listing, and search tools are read-only and cannot modify state. Examples: list campaigns, get promotion details, inspect a trigger, search the knowledge base.

Safe-write tools

A constrained set of tools can create draft assets in Optimove. These tools cannot:

  • Activate or schedule a campaign
  • Send a message to any customer
  • Modify or delete existing campaigns, promotions, triggers, segments, or journeys
  • Change platform settings

Drafts created via the MCP appear inside Optimove exactly like drafts created in the UI. A marketer must explicitly approve and activate them through Optimove — the assistant cannot.

Permissions

The connector inherits the permissions of the authenticated Optimove user. A user who cannot see a campaign in the Optimove UI cannot retrieve it through the MCP. Role-based access controls are enforced at the API layer, not at the prompt layer.

What the connector does not do

  • Does not read or store conversation history
  • Does not access user files outside explicit tool calls
  • Does not transfer money, vouchers, or credits
  • Does not generate images, video, or audio

Tool catalog

Every tool exposed by the connector is listed below, grouped by category and annotated with its safety hint. Read-only tools may run without per-call approval; safe-write tools always prompt for confirmation.

CategoryWhat it doesAnnotation
AnalystRead-only access to Optimove analytics and KPIs. Pulls campaign performance, channel metrics, audience size, segment counts, and tenant-level dashboards.readOnlyHint: true
ExplorerRead-only inspection of Optimove entities. Lists and fetches campaigns, promotions, triggers, journeys, streams, segments, and target groups. Supports filtering by status, channel, date range, and tenant.readOnlyHint: true
KnowledgeSearches Optimove product documentation and returns ranked, cited results. Answers "how does X work" and "how do I configure Y" questions.readOnlyHint: true
Mission ControlRead-only access to platform-health signals: service status, running jobs, recent execution errors, pipeline state.readOnlyHint: true
Builder — Target GroupsCreates a draft target group from a natural-language description. Does not activate or attach to a live campaign.destructiveHint: true
Builder — CampaignsCreates a draft campaign using the public Optimove APIs. Draft only — does not schedule, activate, or send.destructiveHint: true
Builder — TriggersCreates a draft real-time or event trigger. Draft only — does not arm or attach to a live workflow.destructiveHint: true
Builder — StreamsCreates a draft multi-step Stream. Draft only — does not activate.destructiveHint: true

All tool names follow the MCP naming convention — lowercase, snake_case, prefixed with optimove_, and 64 characters or fewer. Each tool ships with a title field and the applicable readOnlyHint or destructiveHint annotation.

Authentication

Optimove MCP uses OAuth 2.0 with Dynamic Client Registration. When you connect from a new client, you are redirected to the Optimove sign-in page, where you authenticate with your normal Optimove credentials and approve the requested scope.

Scopes

The connector requests read access to the entities described above, plus draft-write access for the Builder tools. No other scopes are requested. Scopes can be revoked at any time from the Optimove user profile.

Redirect URIs

The Optimove OAuth provider allowlists the following Claude redirect URIs so that authorization completes cleanly across all Claude surfaces:

https://claude.ai/api/mcp/auth_callback
https://claude.com/api/mcp/auth_callback

Session lifetime

Authorization is per-user and per-client. Tokens are short-lived and refreshed automatically by the host client. Revoking a session in Optimove invalidates the connector immediately.

Limits and constraints

  • Tool responses are capped at 25,000 tokens. Large list operations are paginated.
  • Tool handlers complete within 5 minutes; long-running analytics queries return a job handle for polling.
  • Rate limits follow standard Optimove API rate limits, scoped per user.
  • MVP entities: campaigns, promotions, triggers, journeys, streams, segments, target groups, channels, tenant metadata, Mission Control signals, and product documentation. Other entities will be added in subsequent releases.
  • The MVP supports read tools across all entities. Safe-write tools are scoped to the Builder categories above.

Data handling and privacy

Optimove MCP is a thin protocol layer over the same Optimove APIs that power the product UI. All data accessed through the connector is governed by the existing Optimove Data Processing Addendum (DPA) and security commitments.

Collected:

  • Tool call parameters and results, retained for short-term operational logging and audit
  • OAuth tokens, encrypted at rest and rotated per Optimove's standard token policy
  • Aggregate, anonymized usage telemetry (tool name, latency, success/failure) — never tenant data

Not collected:

  • Conversation history or message content from the host AI client
  • Customer files attached to the conversation in the host client
  • Any data outside the explicit tool call payload

Where data is processed: All processing happens within Optimove's existing tenant infrastructure, in the same region as your Optimove tenant. No tenant data is sent to Anthropic, OpenAI, or any other third party by the Optimove MCP server.

AI training: Optimove does not train AI models on customer data. The MCP server is a stateless gateway between the host AI client and Optimove — it does not forward tenant data to any model provider.

Full privacy policy: optimove.com/privacy-policy

Example prompts for developers and integrators

  • "List all draft campaigns created in the last hour and return their IDs."
  • "Pull the JSON definition of segment lapsed_vip and explain each predicate."
  • "Create a draft trigger that fires on a deposit event with amount greater than 100."

Support

Version history

VersionDateChanges
1.0 (MVP)May 2026Initial public release. Read tools across campaigns, promotions, triggers, journeys, streams, segments, target groups, channels, tenant metadata, Mission Control, and product knowledge. Safe-write tools (drafts) for target groups, campaigns, triggers, and streams.

Updated about 3 hours ago