Sendoso MCP becomes available as an action in Databricks Genie and AI Playground
Sendoso's September 2026 release notes say Sendoso is available as an action inside Databricks Genie and AI Playground, with human approval required for each send.
Sendoso's September 2026 release notes list Sendoso MCP as available in the Databricks Marketplace. After a Databricks admin installs it, Sendoso appears as an action inside Databricks Genie and in agents built and tested in AI Playground. When Databricks flags an account, contact or moment, Sendoso recommends a gift and drafts a note. Nothing sends until a person approves it, and admins choose which Sendoso tools an agent can use, with every call logged.
The details
- Example uses include responding to an intent spike, following up with an engaged webinar attendee and routing a declining account health score to an approved gift.
- GTM engineers can build a workflow once and test it in AI Playground before it goes live.
- Users can ask Genie for send results, including delivered, redeemed and pipeline impact.
- The general Sendoso MCP is available on Core, Advanced and Enterprise plans.
Context
Sendoso opened a request-based beta of its MCP server in June 2026 with Claude and ChatGPT as clients, and moved it to general availability in August, according to its release notes. Our coverage also records Sendoso's August Events Hub for event shipments and an October redesign of its send flow with handwritten note campaigns. Demandbase's September partner update described a separate assistant combining the Sendoso and Demandbase MCPs. The release notes date entries by month only.
Not disclosed
- Exact release date
- Whether Databricks use carries added cost
- Vendor
Sendoso- Category
- Gifting & Direct Mail
- Announcement type
- Partnership
Report an error
Vendors and readers can flag a factual error in this story, or ask for an image or logo to be removed. Email Cora, the editor, with the link. Image and logo removals happen within one business day. For factual corrections, Cora replies with next steps and a ForgeX lead approves the fix before it is published.


