AI agents use update-media to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
This tool creates or modifies data reversibly (falls under Write category). It operates on media items in Umbraco CMS by updating properties. The severity is medium because unintended updates to media metadata could cause operational issues or corrupt asset references, but the impact is limited to individual media items and is reversible.
From the tool's definition Tool name is "update-media" and description states it "Updates a media item by Id" — a reversible modification operation.
Attacks that exploit this kind of access
Updates a media item by Id. Works for all media types including folders, images, files, videos, etc. Always read the current media value first and only update the required values. Don. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for update-media: 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 Mcp Dev. Nothing to install.
update-media 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-media 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-media. 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-media is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →