Dependency findings for a specific app
AI agents call fleet_deps_app to retrieve information from Fleet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves dependency analysis information for a specified application. It has no side effects—it does not execute code, modify dependencies, delete data, or commit financial transactions. It is a read-only operation that queries dependency scan results, consistent with similar tools like 'fleet_deps_status' and 'fleet_audit_status' on the same server which are query/reporting functions.
From the tool's definition Tool name 'fleet_deps_app' and description 'Dependency findings for a specific app' indicate retrieval of dependency analysis results. The verb 'findings' implies querying or reporting existing data without modification.
Documented attack patterns abuse exactly the kind of access fleet_deps_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fleet, and nothing reaches the server without passing your rules. This is the rule we recommend for fleet_deps_app:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_deps_app": {}
}
}fleet_deps_app is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Dependency findings for a specific app. It is categorised as a Read tool in the Fleet MCP Server, which means it retrieves data without modifying state.
Register the Fleet MCP server in PolicyLayer and add a rule for fleet_deps_app: 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 Fleet. Nothing to install.
fleet_deps_app 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 fleet_deps_app 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 fleet_deps_app. 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.
fleet_deps_app is provided by the Fleet MCP server (wrxck/fleet). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fleet, 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 Fleet tools catalogued and risk-classified — across an index of 43,000+ MCP servers.