maid_generate_stubs
AI agents use maid_generate_stubs to create or update resources in Maid Runner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maid Runner environment.
Stub generation creates or modifies code/test files but does not execute arbitrary operations or delete data. This is a write-class tool because it produces new artifacts. Severity is medium due to potential for unintended file creation or overwrites in the project structure.
From the tool's definition Tool name 'maid_generate_stubs' suggests code generation. Server context shows validation/testing tools. 'generate_stubs' typically creates test stub files or placeholder code structures, which are reversible modifications.
Attacks that exploit this kind of access
maid_generate_stubs. It is categorised as a Write tool in the Maid Runner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maid Runner MCP server in PolicyLayer and add a rule for maid_generate_stubs: 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 Maid Runner. Nothing to install.
maid_generate_stubs 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 maid_generate_stubs 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 maid_generate_stubs. 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.
maid_generate_stubs is provided by the Maid Runner MCP server (mamertofabian/maid-runner-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 →