diagnose_proxy
AI agents call diagnose_proxy to retrieve information from Proxy Doctor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a diagnostic function that likely retrieves proxy state or configuration data without modifying anything. The empty description and lack of context about side effects results in moderate confidence, but the diagnostic nature and 'list_fixes' sibling suggest this server performs analysis rather than modification.
From the tool's definition Tool name 'diagnose_proxy' suggests reading/querying proxy configuration or status information. No destructive, write, financial, or execute keywords present.
Attacks that exploit this kind of access
diagnose_proxy. It is categorised as a Read tool in the Proxy Doctor MCP Server, which means it retrieves data without modifying state.
Register the Proxy Doctor MCP server in PolicyLayer and add a rule for diagnose_proxy: 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 Proxy Doctor. Nothing to install.
diagnose_proxy 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 diagnose_proxy 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 diagnose_proxy. 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.
diagnose_proxy is provided by the Proxy Doctor MCP server (Jiansen/proxy-doctor). 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 →