AI agents call read_field to retrieve information from Doc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval only with no side effects. It queries structured document data and returns values without creating, modifying, or deleting any information. Consistent with the Read category for tools that retrieve or query data.
From the tool's definition Tool name is 'read_field' and the description indicates it reads/retrieves values from specified fields (translating to 'Reads the value of a specified field')
Attacks that exploit this kind of access
读取指定字段的值。字段键格式:. It is categorised as a Read tool in the Doc MCP Server, which means it retrieves data without modifying state.
Register the Doc MCP server in PolicyLayer and add a rule for read_field: 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 Doc. Nothing to install.
read_field 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 read_field 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 read_field. 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.
read_field is provided by the Doc MCP server (jiahuidegit/doc-mcp-server). 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 →