AI agents use create_goal to create or update resources in ATMcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ATMcp environment.
This is a Write operation because it creates new data (a goal object) that persists in the team's task/goal system. It is not Read (no retrieval), not Execute (no code/command execution), not Destructive (goals can be modified or archived), and not Financial. Severity is medium because misconfiguration of team goals could misdirect agent work but would not directly compromise security or cause data loss.
From the tool's definition create_goal creates a new goal object in the system, which modifies the state of the shared team goal hierarchy. The description states 'Create a team goal' indicating a persistent write operation.
Attacks that exploit this kind of access
Create a team goal that tasks can roll up into. It is categorised as a Write tool in the ATMcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AT MCP server in PolicyLayer and add a rule for create_goal: 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 ATMcp. Nothing to install.
create_goal 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 create_goal 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 create_goal. 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.
create_goal is provided by the AT MCP server (midcheck/atmcp). 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 →