We’re thrilled to announce the open source release of the Google Ads API Model Context Protocol (MCP) Server, available here. This project marks a significant step in democratizing access to Google Ads data for the next generation of AI tools and agent developers.

The Model Context Protocol (MCP) is the open standard that allows Large Language Models (LLMs), like Google Gemini, to connect with and act upon external data sources and applications. By releasing an MCP Server specifically for the Google Ads API, we are making it possible for any MCP-compatible AI application to understand and analyze advertising campaigns through natural language.

This initial release is read-only, meaning it can be used for reporting and diagnostics but will not make changes to your account.

Please use the GitHub repo for technical issues with the MCP server.

For technical support issues with the API, reach out to the Google Ads API support channel.

If you have other questions or want to discuss this post, please reach out to us on our “Google Advertising and Measurement Community” Discord server.

– Dean Lukies, Google Ads API Team

Starting today, we’re bringing AI Mode in Google Search to more people around the world, launching in more than 35 new languages and over 40 new countries and territorie…

The Stable channel has been updated to 141.0.7390.65/.66 for Windows and Mac and 141.0.7390.65 for Linux, which will roll out over the coming days/weeks. A full list of changes in this build is available in the Log.

Security Fixes and Rewards

Note: Access to bug details and links may be kept restricted until a majority of users are updated with a fix. We will also retain restrictions if the bug exists in a third party library that other projects similarly depend on, but haven’t yet fixed.

This update includes 3 security fixes. Below, we highlight fixes that were contributed by external researchers. Please see the Chrome Security Page for more information.


[$5000][443196747] High CVE-2025-11458: Heap buffer overflow in Sync. Reported by raven at KunLun lab on 2025-09-05

[TBD][446722008] High CVE-2025-11460: Use after free in Storage. Reported by Sombra on 2025-09-23

[$3000][441917796] Medium CVE-2025-11211: Out of bounds read in WebCodecs. Reported by Jakob Košir on 2025-08-29


We would also like to thank all security researchers that worked with us during the development cycle to prevent security bugs from ever reaching the stable channel.


Many of our security bugs are detected using AddressSanitizer, MemorySanitizer, UndefinedBehaviorSanitizer, Control Flow Integrity, libFuzzer, or AFL.

Interested in switching release channels? Find out how here. If you find a new issue, please let us know by filing a bug. The community help forum is also a great place to reach out for help or learn about common issues.

To avoid data bottlenecks when training large models, this guide introduces Grain and ArrayRecord for building high-performance data pipelines.

The Extended Stable channel has been updated to 140.0.7339.240 for Windows and Mac which will roll out over the coming days/weeks.

Today we are releasing the Gemini 2.5 Computer Use model via the API, which outperforms leading alternatives at browser and mobile tasks.

Google AI Plus — our newest AI plan — expands to 36 more countries.

We’re bringing Opal to 15 new countries and making it even easier to build.

Hi everyone! We've just released Chrome Stable 141 (141.0.7390.69) for iOS; it'll become available on App Store in the next few hours.

This release includes stability and performance improvements. You can see a full list of the changes in the Git log. If you find a new issue, please let us know by filing a bug.

Chrome Release Team
Google Chrome

Google Quantum AI’s Chief Scientist. Michel Devoret and former hardware leader John Martinis share the 2025 Nobel Prize in Physics.