AI agents invoke bandit_scan to trigger actions in SAST MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Bandit is a Python static analysis security tool that executes code scanning against source files. The tool runs an external security scanning process. The description is empty, lowering confidence, but given the server context (SAST tools, remote execution on VMs) and sibling tools (all _scan variants), this is clearly an Execute-category tool that triggers an external scanning process.
From the tool's definition Tool name 'bandit_scan' on a server described as integrating 'Bandit' among 15+ static application security testing tools for 'automated vulnerability scanning'
Documented attack patterns abuse exactly the kind of access bandit_scan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAST MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for bandit_scan:
{
"version": "1",
"default": "deny",
"tools": {
"bandit_scan": {
"limits": [
{
"counter": "bandit_scan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bandit_scan stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
bandit_scan. It is categorised as a Execute tool in the SAST MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SAST MCP Server MCP server in PolicyLayer and add a rule for bandit_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 SAST MCP Server. Nothing to install.
bandit_scan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bandit_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 bandit_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.
bandit_scan is provided by the SAST MCP Server MCP server (sengtocxoen/sast-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAST MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
39 SAST MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.