读取文件内容
AI agents call file_reader to retrieve information from MCP Demo Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents without side effects. It performs a simple read operation, making it a Read category tool. Severity is low because file reading alone has minimal blast radius unless sensitive data exposure is a concern in the specific deployment context, but the tool itself is non-destructive and non-modifying.
From the tool's definition Tool name is 'file_reader' and description states '读取文件内容' (read file contents). The description and naming indicate a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
读取文件内容. It is categorised as a Read tool in the MCP Demo Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Demo Server MCP server in PolicyLayer and add a rule for file_reader: 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 Demo Server. Nothing to install.
file_reader 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 file_reader 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 file_reader. 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.
file_reader is provided by the MCP Demo Server MCP server (keosu/mcpdemo). 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 →