scan_mcp_server
AI agents call scan_mcp_server to retrieve information from Mcp Safeguard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Scanning and checking tool definitions are read operations that retrieve or query security metadata about MCP servers without side effects. No modification, deletion, execution, or financial operations are implied. The tool serves a protective, auditing function consistent with the broader server's safeguard mission.
From the tool's definition Tool name 'scan_mcp_server' indicates a scanning/auditing function that examines tool definitions and security configurations without modifying them. The server's stated purpose is to 'provide safeguard capabilities' and protect against injection attacks.
Attacks that exploit this kind of access
scan_mcp_server. It is categorised as a Read tool in the Mcp Safeguard MCP Server, which means it retrieves data without modifying state.
Register the Mcp Safeguard MCP server in PolicyLayer and add a rule for scan_mcp_server: 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 Safeguard. Nothing to install.
scan_mcp_server 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_mcp_server 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_mcp_server. 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_mcp_server is provided by the Mcp Safeguard MCP server (syedanas01/mcp-safeguard). 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 →