qbash Connectors / Execution

Run qbash Tasks through MCP.Give your clients a callable tool.

Package saved qbash Tasks on a hosted MCP server. A connected client supplies the task inputs and receives its result, with execution logs kept in qbash.

Connect Execution free

MCP server

Build a Execution MCP server

Give ChatGPT, Claude and your other AI tools access to Execution through one server. You pick which Execution tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

Connect Execution on the qbash Connectors page.
Create an MCP server and add the Execution tools you want to share.
Paste the server URL into your client. It connects with OAuth or an access token.

Connect a client Package an MCP server

qbash

Call a saved report from chat

Add your reporting task to an MCP server, then ask a connected client to run it with the declared inputs.

Run the weekly search report for the configured property and show its analysis. If the run is still in progress, check its status and retrieve the completed result.

Available tools

Task tools

Each runnable task exposes its declared inputs as a tool schema.

Run status and logs

Use check_task_status and get_task_logs to follow work that continues after the initial call.

Package an MCP server Connect a client

Ways to use Execution

On-demand reporting

Let a teammate ask a connected client to run a saved report with the required inputs.

Shared operations

Expose the same reviewed Python task to several clients while keeping its code and connections in qbash.

How to connect Execution

Create an MCP server and add the saved Tasks your client should be able to run. Share the server with the intended qbash users.

Connect the client using OAuth or an access token as described in the client guide. qbash checks access to the server and the underlying task when a call runs.

Package an MCP server