AI agents use complete_task to create or update resources in Compass MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Compass MCP environment.
This is a Write operation because it creates or modifies data reversibly—marking a task complete changes its status in the workspace state, but the action is reversible (a task can be uncompleted). It does not execute arbitrary operations, delete data irreversibly, or move money.
From the tool's definition The tool 'complete_task' modifies task state by marking a task as complete, which updates persistent task data stored in local markdown files according to the server description.
Documented attack patterns abuse exactly the kind of access complete_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Compass MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for complete_task:
{
"version": "1",
"default": "deny",
"tools": {
"complete_task": {
"limits": [
{
"counter": "complete_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} complete_task stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark a task as complete. It is categorised as a Write tool in the Compass MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Compass MCP server in PolicyLayer and add a rule for complete_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 Compass MCP. Nothing to install.
complete_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_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_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_task is provided by the Compass MCP server (richlira/compass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Compass MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Compass MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.