AI agents call scan_code to retrieve information from Secscan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
SAST tools are inherently read-only operations that parse and inspect code to identify potential issues. The tool does not execute code, modify the codebase, delete data, or commit financial transactions. While the findings may inform security decisions that lead to downstream actions, the tool itself only retrieves and reports vulnerability information.
From the tool's definition Tool performs 'Static analysis (SAST) for code vulnerabilities and unsafe patterns' — it scans and analyzes code without modifying it, executing external code, or producing side effects beyond generating a security report.
Attacks that exploit this kind of access
Static analysis (SAST) for code vulnerabilities and unsafe patterns. It is categorised as a Read tool in the Secscan MCP Server, which means it retrieves data without modifying state.
Register the Secscan MCP server in PolicyLayer and add a rule for scan_code: 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 Secscan. Nothing to install.
scan_code 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_code 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_code. 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_code is provided by the Secscan MCP server (openjkai/secscan_mcp). 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 →