AI agents invoke scan_project to trigger actions in Snyk 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.
This tool executes a security scanning operation against an existing Snyk project. It triggers external processes (Snyk CLI/API calls) rather than merely reading static data. While it doesn't modify or delete data, it actively runs analysis workflows, placing it in the Execute category.
From the tool's definition 'Scan an existing Snyk project' — triggers an active security scan operation via the Snyk CLI/API, which runs external analysis processes
Documented attack patterns abuse exactly the kind of access scan_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Snyk MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for scan_project:
{
"version": "1",
"default": "deny",
"tools": {
"scan_project": {
"limits": [
{
"counter": "scan_project_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scan_project 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.
Scan an existing Snyk project. It is categorised as a Execute tool in the Snyk MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Snyk MCP Server MCP server in PolicyLayer and add a rule for scan_project: 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 Snyk MCP Server. Nothing to install.
scan_project 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 scan_project 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_project. 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_project is provided by the Snyk MCP Server MCP server (sammcj/mcp-snyk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Snyk 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.
4 Snyk MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.