AI agents use publish to create or update resources in Yadisk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yadisk environment.
Publishing a file/folder modifies its sharing/access settings, which is a Write operation—it creates or changes data (the public link and sharing state) reversibly. It does not delete data (Destructive), execute arbitrary code (Execute), move money (Financial), or merely retrieve information (Read).
From the tool's definition The tool 'publish' changes the access state of a file or folder by making it publicly accessible and generating a public URL. This is a reversible modification of resource metadata/properties.
Attacks that exploit this kind of access
Publish a file or folder and return its public URL. It is categorised as a Write tool in the Yadisk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yadisk MCP server in PolicyLayer and add a rule for publish: 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 Yadisk. Nothing to install.
publish 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 publish 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 publish. 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.
publish is provided by the Yadisk MCP server (patr56/yadisk-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 →