AI agents call read_module to retrieve information from Prompts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical modification records for a module before making changes. It performs a read-only operation to access existing data without creating, modifying, deleting, or executing code. The tool is informational in nature, supporting developers in understanding prior changes before making updates. No destructive, financial, or executable side effects are present.
From the tool's definition Tool name 'read_module' and description explicitly state '读取模块记录' (read module records) and 'read...history modification records' — purely retrieval operations with no modification capability.
Attacks that exploit this kind of access
【读取模块记录】修改功能前调用，读取对应模块的历史修改记录。. It is categorised as a Read tool in the Prompts MCP Server, which means it retrieves data without modifying state.
Register the Prompts MCP server in PolicyLayer and add a rule for read_module: 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 Prompts. Nothing to install.
read_module 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_module 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_module. 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_module is provided by the Prompts MCP server (thana0623/pmcp-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 →