AI agents use create_runbook to create or update resources in Runbook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Runbook environment.
Creating files is a reversible write operation. The severity is medium rather than low because runbooks can contain instructions for significant operations, and an AI agent creating arbitrary runbook files could potentially set up malicious automation. However, without execution capability alone, the impact is contained to file creation.
From the tool's definition Tool description states 'Create a runbook file and save the content' — this is a create operation that generates new files.
Attacks that exploit this kind of access
Create a runbook file and save the content. It is categorised as a Write tool in the Runbook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Runbook MCP server in PolicyLayer and add a rule for create_runbook: 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 Runbook. Nothing to install.
create_runbook 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_runbook 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_runbook. 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_runbook is provided by the Runbook MCP server (runbookai/runbook-mcp-server). 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 →