Update dependencies in Metalsmith plugin(s) using npm-check-updates.
AI agents use update-deps to create or update resources in Metalsmith Plugin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Metalsmith Plugin environment.
Updating dependencies modifies project configuration and installed packages reversibly (via npm/yarn rollback capability). This is a Write operation—it creates or modifies data without permanent destruction.
From the tool's definition Tool description states 'Update dependencies in Metalsmith plugin(s) using npm-check-updates' — explicitly performs package dependency updates which modify package.json and lockfiles.
Attacks that exploit this kind of access
Update dependencies in Metalsmith plugin(s) using npm-check-updates. It is categorised as a Write tool in the Metalsmith Plugin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Metalsmith Plugin MCP server in PolicyLayer and add a rule for update-deps: 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 Metalsmith Plugin. Nothing to install.
update-deps 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 update-deps 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 update-deps. 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.
update-deps is provided by the Metalsmith Plugin MCP server (metalsmith-plugin-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 →