Use Console from Python

Use mcp_console to call Console from Python or add it to a model framework. This is the client package, not the Python environment in which the agent’s analysis runs. It requires Python 3.11 or newer.

The documentation covers the shared workbench: sessions, packages, sandbox permissions, and recordings.

Call Console directly

Install the client extra in your application’s environment:

pip install 'mcp-console[client]'

from mcp_console import MCPConsole

with MCPConsole() as console:
    print(console.send(python="values = [2, 4, 6]; values"))
    print(console.send(python="sum(values)"))

Keep the connection open to retain state. Closing it ends the session; reconnecting starts a new one.

Use AsyncMCPConsole with async with and await for asynchronous code. Enter and close an async connection in the same task. The API reference documents launch commands, working directories, environment options, and exact signatures.

Choose a model integration

Install the extra for your framework. Each reference page provides a complete example, including setup and cleanup.

Framework	Extra	Existing Console connection	Framework-managed connection
chatlas	`chatlas`	tool	register
`openai` — Responses API	`openai`	responses_tool	Application-owned loop.
`openai-agents` — Agents SDK	`openai-agents`	agents_tool	agents_server
`openai-codex` — Codex SDK	`codex`	—	server supplies configuration; it does not open a connection.
Anthropic	`anthropic`	tool	tools

Your application still owns its model client, chat or agent, and any function-calling loop. Creating a Console tool does not choose a model.

Use the supplied adapters so the model receives the connected server’s actual schema. Inferring a schema from console.send annotations loses configured fields. Recreate adapters after reconnecting. For chatlas, use set_tools() on a new chat to retain the adapter’s explicit schema.

Work with the session

The shared guides explain sessions and languages, packages and environments, sandbox permissions, and recordings and reports. These describe the same workbench your agent uses from Python.

Drive send directly walks through collecting unfinished results, answering input, interrupting work, and restarting. The MCPConsole reference documents result handling and connection cleanup, including KeyboardInterrupt.

For exact dependency fields and replacement rules, see Requirements and the send reference. To prepare data and customize what the model sees, follow Build a data assistant.