Navan, the business travel and expense platform, announced the launch of its Model Context Protocol (MCP), which allows customers to connect Navan to their existing AI tools and securely access their travel and expense data together through simple queries that use natural language. 

Navan’s MCP, said the announcement, gives administrators and finance leaders the ability to analyze spend, booking or policy data by simply chatting with their preferred AI interface. By plugging directly into workflows that enterprises rely on every day, said the announcement, Navan MCP acts as a universal power adapter that transforms complex backend infrastructure into conversational clarity. 

The initial MCP deployment, said the announcement, provides a read-only experience for gathering corporate travel and expense intelligence. The MCP also establishes the necessary foundation to support upcoming write-access tools including approving out-of-pocket expenses, updating travel policies and broader agent integrations for users to book travel within their preferred interface. 

Once configured, the MCP allows travel and finance admins to pull aggregate program insights and live transaction timelines by simply querying inside their preferred environments like Claude, ChatGPT, Cursor or other MCP-compatible systems. Administrators can run sophisticated analysis through conversational prompts, such as:  

• “Where is out-of-policy spend the highest across our global teams?”
• “Show me every flagged expense over $500 from Q2 that hasn’t been approved yet.”   
• “Summarize each department’s spend by category for the last quarter.”

Dane Molter, senior vice president of travel marketplace at Navan, said the MCP “is an important step in bringing our entire ecosystem directly into employees’ everyday workflows.”  He added, “We’ve built this using over a decade of Navan’s data, making it one of the most context-aware MCPs for travel and setting the stage for even more functionality in the future.”