Submit final output and mark task completed.
AI agents use submit_my_output to create or update resources in Dag Planner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dag Planner environment.
The tool creates or modifies persistent state (task completion status and output data) within the DAG planner system. While reversible via other tools or replay, submitting task output is a write that affects downstream task dependencies and workflow execution. Not Destructive (not irreversible deletion), not Execute (it does not run arbitrary code), not Financial.
From the tool's definition Tool description states 'Submit final output and mark task completed' — this modifies task state durably by recording completion and output, making it a write operation.
Attacks that exploit this kind of access
Submit final output and mark task completed. It is categorised as a Write tool in the Dag Planner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dag Planner MCP server in PolicyLayer and add a rule for submit_my_output: 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 Dag Planner. Nothing to install.
submit_my_output 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 submit_my_output 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 submit_my_output. 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.
submit_my_output is provided by the Dag Planner MCP server (shubhamnegi/dag-planner-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 →