---
title: Jobs
editUrl: https://github.com/Cratis/Chronicle.Mcp/edit/main/Documentation/operate-side/jobs.md
description: Chronicle runs long-lived work — replays, projections rebuilds, and other maintenance — as jobs. These tools let an agent list jobs, inspect their…
---

Chronicle runs long-lived work — replays, projections rebuilds, and other maintenance — as jobs. These tools let an agent list jobs, inspect their progress and steps, and control their lifecycle.

The default `ReadOnly` profile exposes job inspection only. `stop_job`, `resume_job`, and `delete_job` require the `Mutation` profile and a matching grant for the principal, event store, namespace, operation, and job ID. See [Deployment profiles](/chronicle-mcp/deployment-profiles/).

## Tools

| Tool | Description |
| --- | --- |
| `list_jobs` | List all jobs in a namespace, optionally filtered by job status. |
| `get_job` | Get a specific job by id, including full details and status changes. |
| `get_job_steps` | Get the steps of a specific job, optionally filtered by step status. |
| `stop_job` | Mutation profile: stop a specific job. It transitions to a stopped status. |
| `resume_job` | Mutation profile: resume a specific stopped job. |
| `delete_job` | Mutation profile: delete a specific job. It transitions to a removing status. |

## Typical flow

1. `list_jobs` — see what is running or has run, filtered by status when you only care about, say, failed jobs.
2. `get_job` — inspect one job's details and the history of its status changes.
3. `get_job_steps` — drill into the individual steps to see where a job is or where it stopped.
4. `stop_job` / `resume_job` / `delete_job` — control the job once you understand its state.

## A note on control operations

`stop_job`, `resume_job`, and `delete_job` change a running system. Have the agent confirm the job id and its current state — with `get_job` — before invoking them, the same care you would take from the CLI.

The server tells your MCP client that these three tools change state, so a client that asks before state-changing calls asks for them. All three are safe to repeat. `stop_job` and `resume_job` are not destructive — a stopped job keeps its progress and can be resumed. `delete_job` is destructive and irreversible: once a job is removed, it cannot be recovered. MCP clients should ask the user to confirm the specific job and scope before calling it; the server does not prompt. See [Which tools change state](/chronicle-mcp/concepts/#which-tools-change-state).