AI agents call search-document 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 retrieves or queries document data without creating, modifying, deleting, or executing operations. It has no side effects on the CMS state. The pagination parameters (skip, take) confirm it is designed for safe data retrieval. Classified as Read with low severity due to minimal blast radius if misused by an agent—worst case would be unauthorized information disclosure of existing documents.
From the tool's definition Tool name 'search-document' combined with description 'Searches for documents by query, skip, and take' indicates a query/search operation with pagination parameters.
Attacks that exploit this kind of access
Searches for documents 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-document: 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-document 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-document 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-document. 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-document 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 →