Detect runtime features (V2 compatible). Deprecated: Use system/info instead.
AI agents call features_detect to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs detection and inspection of runtime features, which is a read-only operation that queries system state without side effects. The deprecation notice directing users to 'system/info' reinforces that this is an informational/diagnostic tool. No data is created, modified, deleted, or executed—only features are detected and reported.
From the tool's definition Tool name 'features_detect' and description 'Detect runtime features' indicates inspection/querying of system capabilities without modification. The tool retrieves information about runtime features.
Attacks that exploit this kind of access
Detect runtime features (V2 compatible). Deprecated: Use system/info instead. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for features_detect: 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.
features_detect 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 features_detect 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 features_detect. 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.
features_detect 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.