Discover all MCP server configs and test their connections via JSON-RPC handshake
AI agents call scan to retrieve information from Mcp Doctor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs discovery and connection testing, which are read-only operations. It retrieves information about MCP server configurations and validates connectivity through handshakes. There are no side effects, modifications, code execution, or destructive operations. The only security concern is the scope of what it might read (server configs), but the action itself is informational, making it low severity.
From the tool's definition Tool is described as 'Discover all MCP server configs and test their connections via JSON-RPC handshake' — it reads/discovers configurations and tests connectivity without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Discover all MCP server configs and test their connections via JSON-RPC handshake. It is categorised as a Read tool in the Mcp Doctor MCP Server, which means it retrieves data without modifying state.
Register the Mcp Doctor MCP server in PolicyLayer and add a rule for scan: 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 Doctor. Nothing to install.
scan 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 scan 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 scan. 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.
scan is provided by the Mcp Doctor MCP server (realwigu/mcp-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 →