AI agents call search-element to retrieve information from Mcp Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query operation that retrieves or lists elements from the Umbraco CMS without creating, modifying, or deleting data. Search operations are read-only and pose minimal security risk in isolation, though the blast radius depends on what sensitive data the search might expose.
From the tool's definition Tool name is 'search-element' and description states it 'Searches for elements by query, skip, and take.' The use of 'Searches' and parameterization by query/skip/take indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
Searches for elements by query, skip, and take. It is categorised as a Read tool in the Mcp Dev MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for search-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.
search-element is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search-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 search-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.
search-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 →