Mark the plan as successfully completed. Call this after all nodes have been executed.
AI agents use plan_completed to create or update resources in Overture — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Overture environment.
The tool updates the completion status of a plan, which is a data modification but not destructive (status can be reset) and not autonomous execution (it documents completion rather than triggering new actions). The moderate severity reflects that marking incorrect plan completion could mislead monitoring and approval workflows, affecting visibility and control of AI agent operations.
From the tool's definition 'Mark the plan as successfully completed' indicates a state-change operation that modifies plan metadata/status. This is a reversible write operation on the plan record.
Documented attack patterns abuse exactly the kind of access plan_completed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Overture, and nothing reaches the server without passing your rules. This is the rule we recommend for plan_completed:
{
"version": "1",
"default": "deny",
"tools": {
"plan_completed": {
"limits": [
{
"counter": "plan_completed_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}plan_completed 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 the plan as successfully completed. Call this after all nodes have been executed. It is categorised as a Write tool in the Overture MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Overture MCP server in PolicyLayer and add a rule for plan_completed: 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 Overture. Nothing to install.
plan_completed 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 plan_completed 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 plan_completed. 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.
plan_completed is provided by the Overture MCP server (sixhq/overture). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Overture tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Overture tools catalogued and risk-classified — across an index of 42,500+ MCP servers.