Dropbox's rebuilt API documentation adds two features that help developers work on an integration: in-browser endpoint testing that returns real API responses, and a connection for compatible AI tools through MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition →, a standard interface for supplying tools with external information.
These serve different purposes. Interactive testing lets a developer inspect what an API call actually returns. The documentation connection gives an AI assistant access to the reference material it needs to explain endpoints and help write integration code. The announced MCP service supplies documentation; the browser's API-testing capability is a separate feature.
Key takeaways · AI-distilled
Dropbox's rebuilt API reference at docs.dropboxapi.com lets developers test endpoints directly in the browser, issuing real API calls and seeing real responses without a separate tool.
An embedded AI assistant answers questions about specific endpoints and offers code examples inline in the documentation.
AI coding tools can connect to Dropbox's docs via an MCP server (docs.dropboxapi.com/_mcp/server), reachable through built-in "Connect to Claude Code" or "Connect to Cursor" actions on API reference pages.
Terms in this piece · Glossary
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
articleHow AI-assisted development helped us build the new Dropbox experienceDaniel Reiter Horn,Rich Chan,Pravi Garg,Sourabh Yerfule,Gennadiy Civil
articleWhat Dropbox has learned from deploying AI at company scaleDropbox Team
articleHow our universal content processing platform Riviera evolved for AI and beyondIlya Yakovlev,Andrew Cheung,Binoy Dash