sales_ops · saas · workflow
HubSpot builds a remote MCP server to expose CRM data to AI agents
HubSpot needed to connect their CRM to AI agents, with 75% of customers already using ChatGPT, but the MCP standard lacked built-in auth support and no agent protocol had yet emerged in the AI era, making it unclear how to expose CRM data securely at scale.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · OpenAI MCP adoption triggers build
HubSpot decided to build an MCP server after OpenAI adopted MCP and all major players followed within 48 hours.
Tools used
Java MCP SDKClaude CodeDropwizardOAuthBreeze Assistant
Outcome
HubSpot became the first CRM with a remote MCP server and the first CRM connector to OpenAI, delivered in under four weeks, with internal AI tool adoption reaching 70-80% and customers actively using the connector.
Results
Time savedless than four weeks
Volume75%
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes, 2 dropped as unverifiable.
agentic workflowai agentcode generationknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedtools describedvendor confirmedsoftwareemployee productivitytime savedtechnical build writeupback office opssales opsagentic task executiondata sync enrichment