create_debt
AI agents use create_debt to create or update resources in Service Atlas MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Service Atlas MCP Server environment.
The tool creates debt records in a service dependency tracking system. This is a Write action because it creates new data reversibly (debt can presumably be updated or removed). Severity is medium because creating incorrect debt records could mislead teams about their technical obligations, but it does not directly delete data, execute external code, or move money.
From the tool's definition Tool name is 'create_debt' which explicitly indicates creation of a new data object. The description is empty, providing no additional context.
Attacks that exploit this kind of access
create_debt. It is categorised as a Write tool in the Service Atlas MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Service Atlas MCP Server MCP server in PolicyLayer and add a rule for create_debt: 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 Service Atlas MCP Server. Nothing to install.
create_debt 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_debt 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_debt. 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_debt is provided by the Service Atlas MCP Server MCP server (service-atlas/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 →