Implement v1.0.0 core features and refactor codebase

[Professor-Codephreak]

This major update implements the core functionalities for mcp.agent v1.0.0 as outlined in the README.md and initial todo.md.

Key changes include:

• Implemented FirestoreBqJobStore and BqJobInfo for persistent BQ job tracking.
• Implemented GCS tools: list_buckets, list_objects, signed URLs (read/write), write_string_object.
• Implemented BigQuery tools: list_datasets, list_tables, get_table_schema, submit_query (async), get_job_status, get_query_results.
• Implemented a background BQ job poller to update job statuses from BQ API to Firestore.
• Implemented core server logic for STDIO and SSE (using aiohttp) transports in server.py.
• Consolidated cli.py as the sole entry point, removing redundancy with the old server.py content.
• Refactored gcp_tools module: separated GCS and BQ logic into storage.py and bigquery.py respectively.
• Updated gcp_tools/init.py with a new ALL_TOOLS_MAP for dispatching to the new stateless tools.
• Removed legacy mcp_agent/context.py.
• Improved code quality with consistent logging, enhanced type hints, and configurable BQ poll interval.
• Updated README.md extensively to reflect the new architecture, implemented tools, and usage instructions.
• Updated todo.md to mark completed tasks and identify next steps (like tool schema definitions).

[gemini-code-assist]

Summary of Changes

Hello @Professor-Codephreak, 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 delivers the core features for mcp.agent v1.0.0, establishing a stateless and scalable integration with Google Cloud Storage and BigQuery. It introduces persistent BigQuery job tracking via Firestore and refactors the codebase for improved modularity and maintainability, while also enhancing server communication transports.

Highlights

• Core Feature Implementation: Implemented key functionalities for mcp.agent v1.0.0, including persistent BigQuery job tracking using Firestore, and a comprehensive set of GCS and BigQuery tools.
• Stateless Architecture: Transitioned to a stateless design for GCP tool interactions, removing context-setting tools and requiring explicit resource identifiers, which enhances scalability.
• Asynchronous BigQuery Operations: Introduced an asynchronous pattern for BigQuery queries with server-side polling and persistent job status tracking in Firestore, allowing for robust long-running operations.
• Codebase Refactoring: Consolidated the application entry point to cli.py, modularized GCP tool implementations into separate storage.py and bigquery.py files, and removed legacy components, improving code organization and maintainability.
• Enhanced Server Transports: Implemented core server logic for both STDIO and SSE (Server-Sent Events) transports using aiohttp, providing flexible communication options for the agent.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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

The code changes introduce the ability to load multiple signed images to a registry using a bulk load feature. The changes look good, but there are a few things that could be improved. The pre-flight check for asynchronous functions is not correctly implemented. The implementation of get_bq_client appears to be a placeholder and is not valid Python code. The get_loop() method is deprecated since Python 3.10 and will be removed in a future version. Using asyncio.sleep(3600) to keep the server running works, but it's not the most idiomatic way to express "wait forever".