# browser-use 1.0.7 stops MCP calls timing out at 60 seconds

published: 2026-11-20T20:05:37.497Z
topic: mcp
source: https://github.com/browser-use/browser-use/releases/tag/1.0.7
url: https://aiagentnews.io/stories/browser-use-1-0-7-stops-mcp-calls-timing-out-at-60-seconds

browser-use 1.0.7 changes its MCP browser_exec tool so that long-running calls reply with partial output after 50 seconds instead of hitting client timeouts. Clients with a 60-second limit, such as Cursor, should get a result rather than a request timeout.

The Python package browser-use released version 1.0.7, which changes how long-running MCP calls to browser_exec behave. Previously, MCP calls could time out at 60 seconds. Now a call still running after 50 seconds replies with the output produced so far, while the code keeps running in the cell.

Calling browser_exec again with empty code returns the rest of the output. Calls that finish within 50 seconds reply as they did before. The release also updates the README, with a Browser Use for enterprises section and a restored Cloud API key link in the Python quickstart.

Skills, the README, the CLI and MCP now ask coding agents for integration feedback.

## Why it matters if you build agents

If you run agents against browser-use's MCP server, a long browser_exec call no longer has to finish inside a client's 60-second window to return something. Agents should call browser_exec again with empty code to collect the remaining output, since the cell continues running after the partial reply.
