AI agents call get_tool_info 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.
The tool name and context strongly suggest read-only functionality—retrieving metadata about tools. The empty description limits confidence, but the naming pattern and sister tools (all list/get/info operations) indicate a Read classification. No evidence of side effects, modification, execution, or destruction.
From the tool's definition Tool name 'get_tool_info' suggests information retrieval. Sibling tools like 'list_all_tools', 'list_available_servers', and 'get_loaded_servers' indicate this server primarily exposes query/inspection operations. Description is empty, reducing confidence.
Attacks that exploit this kind of access
get_tool_info. 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 get_tool_info: 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.
get_tool_info 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 get_tool_info 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 get_tool_info. 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.
get_tool_info is provided by the MCP Proxy MCP server (lizthedeveloper/mcp_proxy). 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 →