ZoomInfo Launches MCP Connector and API on Snowflake

ZoomInfo has made ZoomInfo MCP and the ZoomInfo API available in Snowflake's AI Data Cloud. Business users can ask questions of ZoomInfo data in natural language inside Snowflake CoWork, and data teams can enrich Snowflake tables in real time or in bulk. Both connections run through GTM.AI, ZoomInfo's headless GTM context layer.

ZoomInfo MCP connects to Snowflake CoWork and Cortex Agents as an MCP connector. Once it is connected, a Cortex agent can search, enrich, and research companies and contacts from ZoomInfo's GTM Context Graph, which covers more than 100 million companies, 500 million contacts, and billions of signals. It returns that context alongside the customer's own Snowflake data in a single cited answer.

For data teams, the ZoomInfo API adds programmatic access to Search, Enrich, Lookup, Bulk, and Monitoring endpoints from Snowflake Tasks, Streams, Snowpark pipelines, and external functions. Bulk enrichment handles up to 10,000 records per request and 200,000 records per query. Both connections extend ZoomInfo's Data Cubes on Snowflake Marketplace, which deliver company, contact, intent, hierarchy, and IP datasets into a customer's Snowflake account on a schedule.

The integration supports the following work across sales, operations, and data teams:

• Account health research and flagging recent leadership changes. Sellers' internal usage data in Snowflake is combined with ZoomInfo Scoops and Account Research in one answer.
• Buying-committee mapping, to find missing stakeholders on open opportunities with verified titles and contact details.
• Real-time lead enrichment, as new records landing in a Snowflake staging table are enriched on arrival.
• Bulk CRM backfill: Nightly Bulk API jobs keep firmographic and technographic fields current across every account in the warehouse.
• Signal-driven scoring, with Intent and Scoops data feed propensity models built in Snowpark.
• Change detection:Monitoring API webhooks refresh only the Snowflake rows whose ZoomInfo records have changed.

"An agent is only as useful as the context it can reach," said Dennis Sevilla, chief strategy officer at ZoomInfo, in a statement. "Snowflake customers already keep their pipeline, usage, and account history in Snowflake. GTM.AI adds the outside view: 100 million companies, 500 million contacts, and billions of signals, under the same permissions teams use in ZoomInfo today. So an agent in Snowflake CoWork can tell a rep what changed at an account, not just what was logged last quarter."

"Snowflake CoWork is designed to help every team ask questions of their enterprise data and get answers they can trust," said Rodrigo Rocha, vice president of global independent software vendor and enterprise technology partnerships at Snowflake, in a statement. "With ZoomInfo available as an MCP connector, our customers can bring ZoomInfo’s verified company, contact, and buying-signal context into Cortex Agents alongside the data they already govern in Snowflake. That gives revenue and data teams a fuller picture of every account, inside the environment they already use."

Snowflake joins a growing list of GTM.AI integrations, including Salesforce, HubSpot, Microsoft, Gong, LeanData, Claude, ChatGPT, Replit, and Superhuman Go. Every surface reads from the same GTM Context Graph and runs under the same governance.

Governance stays tied to existing permissions. ZoomInfo MCP and the ZoomInfo API authenticate through OAuth 2.0, and every call inherits the user's ZoomInfo role-based permissions. Only a Snowflake admin can expose ZoomInfo to Cortex Agents, and all usage is logged in ZoomInfo's audit framework.

ZoomInfo on Snowflake adds verified external intelligence, so agent answers and pipeline outputs reflect what is changing at an account as well as what is already recorded.