AI agents use complete_dev_task to create or update resources in Tickr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tickr environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
branch | string | — | Git branch name |
summary | string | Yes | Summary of what was done |
commit_hash | string | — | Last commit SHA |
assignment_id | string | Yes | UUID of the dev agent assignment |
files_changed | array | — | List of changed file paths |
Parameters from the server's own tool schema.
This tool creates or modifies data reversibly by updating task status to 'completed' and recording associated metadata (summary, branch name, commit hash). It does not execute external code, delete data irreversibly, or move funds. The modifications are reversible (task status can be changed back), so it falls under Write rather than Destructive or Execute.
From the tool's definition Tool description states 'Mark a dev agent task as completed' — this is a state-change operation that modifies task records (marking completion status).
Attacks that exploit this kind of access
Mark a dev agent task as completed with summary, branch name, and commit hash. It is categorised as a Write tool in the Tickr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
complete_dev_task accepts 5 parameters: branch, summary, commit_hash, assignment_id, files_changed. Required: summary, assignment_id. The full parameter table on this page comes from the server's own tool schema.
Register the Tickr MCP server in PolicyLayer and add a rule for complete_dev_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tickr. Nothing to install.
complete_dev_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the complete_dev_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for complete_dev_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
complete_dev_task is provided by the Tickr MCP server (@k-system/tickr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →