scaffold_script
AI agents invoke scaffold_script to trigger actions in Metis Public Health. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The description is empty, so classification relies on the tool name alone. 'scaffold_script' most likely creates a script template or boilerplate (Write), but given the sibling tool 'analyze_script' and the general pattern of script-related tools, it could also involve executing or setting up executable code. 'Scaffold' typically means generating a code/file structure, which leans toward Write or Execute.
From the tool's definition Tool name 'scaffold_script' combined with sibling tool 'analyze_script' suggests this tool generates or sets up script structures/templates, potentially writing or executing code
Attacks that exploit this kind of access
scaffold_script. It is categorised as a Execute tool in the Metis Public Health MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for scaffold_script: 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 Metis Public Health. Nothing to install.
scaffold_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the scaffold_script 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 scaffold_script. 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.
scaffold_script is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →