Overhaul MCP docs for Custom DC bundled server

[kmoscoe]

This PR removes most of the text pertaining to MCP in Custom DC. It also updates the architecture diagrams, reorders pages in the navigation, corrects wrong info about API keys, and adds references to MCP throughout.

Staged at http://bullie.svl.corp.google.com:4000

[gemini-code-assist]

Summary of Changes

Hello @kmoscoe, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly refines the documentation for integrating the Model Context Protocol (MCP) with Custom Data Commons bundled servers. The changes aim to simplify the setup and usage experience by focusing on the built-in MCP server, providing clear instructions for connecting AI agents, and updating the overall structure and accuracy of related pages.

Highlights

• MCP Documentation Overhaul: The documentation for the Model Context Protocol (MCP) within Custom Data Commons has been significantly revised to focus on the bundled server approach.
• Streamlined AI Agent Connection: New, clearer instructions are provided for connecting AI agents (including Gemini CLI and a sample agent) to the integrated MCP server, removing the need for separate server deployments.
• Navigation and Workflow Updates: The navigation order of several documentation pages has been adjusted for improved flow, and workflow steps have been updated to reflect the new MCP integration.
• New Search Scope Configuration: A new dc_search_scope variable has been introduced, allowing users to control whether AI agent queries search base, custom, or both datasets.
• Removed Outdated Content: Extensive sections detailing the deployment of standalone MCP servers in Google Cloud and local environments have been removed, simplifying the documentation.

Changelog

• custom_dc/advanced.md
  • Updated the navigation order of the page.
• custom_dc/custom_data.md
  • Adjusted the indentation of an image tag.
• custom_dc/deploy_cloud.md
  • Updated the navigation order of the page.
  • Revised the workflow step number from 4 to 5.
  • Added the dc_search_scope variable to deployment options.
  • Included a new section for connecting AI agents to the MCP server.
• custom_dc/faq.md
  • Updated the navigation order of the page.
• custom_dc/index.md
  • Added the MCP server to the feature capabilities table.
  • Removed a blank line for formatting consistency.
  • Corrected 'container' to 'containers' in a description.
  • Included an optional step for configuring AI agents in the workflow.
• custom_dc/launch_cloud.md
  • Updated the navigation order of the page.
• custom_dc/quickstart.md
  • Added the MCP server to the list of components within the services Docker container.
  • Updated the description of started development/debug versions to include the MCP server.
• custom_dc/run_mcp_tools.md
  • Updated the navigation order of the page.
  • Removed extensive content on running standalone MCP servers locally and in GCP.
  • Added new sections for configuring the bundled MCP server and connecting AI agents (Gemini CLI, sample agent) to it.
• custom_dc/troubleshooting.md
  • Updated the navigation order of the page.
• mcp/host_server.md
  • Added step numbering to the instructions for configuring Gemini CLI and the sample agent.
• mcp/run_tools.md
  • Removed a blank line for formatting consistency.
  • Added uv as a prerequisite for the sample agent.
  • Included an anchor for the 'Customize the agent' section.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request overhauls the documentation for the Model Context Protocol (MCP) to reflect its integration into the Custom Data Commons bundled server. The changes are extensive, removing outdated information about running a separate MCP server and adding details about the new bundled component. The architecture diagrams, navigation order, and workflow steps have been updated accordingly. Overall, the changes make the documentation much clearer and more accurate. I've found a few minor issues like typos and broken links in the markdown files and have provided suggestions to fix them.