readDocument
AI agents call readDocument to retrieve information from Cloudflare Remote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'readDocument' follows standard read operation naming patterns (e.g., 'read', 'get', 'fetch'). Combined with the server context that includes listing and searching documents, this tool appears to retrieve or query document data without modification.
From the tool's definition Tool name 'readDocument' indicates document retrieval. The description is empty, providing no additional context, but the naming convention strongly suggests a read operation with no side effects.
Attacks that exploit this kind of access
readDocument. It is categorised as a Read tool in the Cloudflare Remote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cloudflare Remote MCP Server MCP server in PolicyLayer and add a rule for readDocument: 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 Cloudflare Remote MCP Server. Nothing to install.
readDocument 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 readDocument 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 readDocument. 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.
readDocument is provided by the Cloudflare Remote MCP Server MCP server (phkus/craft-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 →