Publishes an element by Id. IMPORTANT: If workflow approval is required, use the initiate-workflow-action function instead. This function bypasses approval workflows and publishes directly to the live site. When the culture is not provided, the default culture is null. When the schedule is not pr...
AI agents invoke publish-element to trigger actions in Mcp Dev. 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.
Publishing content directly to a live site is an external operation with significant real-world impact. It bypasses approval workflows, meaning an AI agent could unilaterally push unreviewed content to production. This is not a simple data write (reversible, internal) but an action that triggers a live deployment, making it Execute with high severity due to the blast radius of publishing arbitrary content publicly.
From the tool's definition 'Publishes an element by Id' and 'bypasses approval workflows and publishes directly to the live site'
Attacks that exploit this kind of access
Publishes an element by Id. IMPORTANT: If workflow approval is required, use the initiate-workflow-action function instead. This function bypasses approval workflows and publishes directly to the live site. When the culture is not provided, the default culture is null. When the schedule is not provided, the default schedule is null. It is categorised as a Execute tool in the Mcp Dev MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for publish-element: 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.
publish-element 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 publish-element 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-element. 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-element 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 →