AI agents call read_tool to retrieve information from Mcp Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata (input schema) about other tools. It queries information without modifying, executing, or deleting anything. The operation is non-destructive and has no external side effects beyond returning data that likely already exists in the system's tool definitions.
From the tool's definition Tool name is 'read_tool' and description states 'Read the full input schema for a specific tool on a server' — this is purely a retrieval operation with no side effects.
Attacks that exploit this kind of access
Read the full input schema for a specific tool on a server. It is categorised as a Read tool in the Mcp Proxy MCP Server, which means it retrieves data without modifying state.
Register the Mcp Proxy MCP server in PolicyLayer and add a rule for read_tool: 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 Proxy. Nothing to install.
read_tool 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_tool 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_tool. 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_tool is provided by the Mcp Proxy MCP server (shengxiao20/mcp-proxy-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 →