Download an npm MCP server package and scan it for backdoors, exfiltration code, obfuscation, dangerous code execution, and supply chain risks. Returns a full security report with severity ratings.
AI agents call scan_package to retrieve information from Mcp Shield without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
scan_package is a security auditing tool that performs static analysis on downloaded packages. It reads and examines code to identify risks but does not execute the code, modify user files, delete anything, or move money. The tool itself is defensive in nature — its purpose is to help users avoid dangerous MCP servers. Even though it downloads a package, this is a temporary read operation for analysis purposes.
From the tool's definition Tool 'downloads' and 'scans' a package, producing a 'security report' — it analyzes and retrieves data about code without modifying, deleting, or executing anything on the user's system.
Attacks that exploit this kind of access
Download an npm MCP server package and scan it for backdoors, exfiltration code, obfuscation, dangerous code execution, and supply chain risks. Returns a full security report with severity ratings. It is categorised as a Read tool in the Mcp Shield MCP Server, which means it retrieves data without modifying state.
Register the Mcp Shield MCP server in PolicyLayer and add a rule for scan_package: 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 Shield. Nothing to install.
scan_package 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_package 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_package. 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_package is provided by the Mcp Shield MCP server (muhannad-hash/mcp-shield). 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 →