My custom tool
AI agents call my-tool as a supporting operation in Claude Flow workflows.
The tool name and description provide no meaningful information about what the tool does, what data it accesses, or what side effects it may have. With no actionable evidence, no specific risk category can be reliably assigned. Confidence is very low; the classification should be revisited once a proper description is available.
From the tool's definition Tool name: 'my-tool', description: 'My custom tool' — both are entirely generic and uninformative.
Attacks that exploit this kind of access
My custom tool. It is categorised as a Other tool in the Claude Flow MCP Server, which means it performs auxiliary operations.
Register the Claude Flow MCP server in PolicyLayer and add a rule for my-tool: 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 Claude Flow. Nothing to install.
my-tool is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the my-tool 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 my-tool. 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.
my-tool is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.