AgentMode ✨

What is AgentMode?

AgentMode is an all-in-one Model Context Protocol (MCP) server that connects your coding AI to dozens of databases, data warehouses, data pipelines, cloud services, and more. It is designed to streamline development workflows by providing seamless integration with various data and cloud platforms.

How to use AgentMode?

You can install AgentMode either as a VS Code extension (install from the marketplace, then start the MCP server via the Command Palette using “MCP: List Servers”) or as a Python package (run uv init, uv add agentmode, and uv run agentmode). Once started, go to http://localhost:13000/setup to configure connections.

Key features of AgentMode

• Connects coding AI to databases, data warehouses, and data pipelines.
• Allows the AI to use a web browser.
• Provides access to production service logs.
• Supports cloud services (AWS, Azure, Google Cloud – coming soon).
• Credentials are stored locally on your machine.

Use cases of AgentMode

• Query MySQL, PostgreSQL, Snowflake, or BigQuery directly from your AI assistant.
• Interact with Airflow or Prefect data pipelines for real‑time or batch processing.
• View and analyze logs from your production services within the AI chat.
• Give your coding AI the ability to browse the web as part of its workflow.

FAQ from AgentMode

What exactly does AgentMode do?

AgentMode uses the Model Context Protocol (MCP) to let your coding AI access and query databases, data warehouses, data pipelines, cloud services, and more – all through a single server.

How can I install AgentMode?

Two ways: install the VS Code extension from the marketplace, or install the Python package via uv add agentmode and run uv run agentmode. Full setup instructions are in the README.

Where are my connection credentials stored?

All credentials are stored locally on your machine. No data leaves your environment.

What data sources are currently supported?

AgentMode supports databases (MySQL, PostgreSQL, etc.), data warehouses (Snowflake, BigQuery, Redshift, etc.), data pipelines (Airflow, Prefect, etc.), and cloud services (AWS, Azure, Google Cloud – coming soon).

Where can I get help or contribute?

Open an issue on the GitHub repository or chat on the Discord server. Contributions are welcome.