Evaluate feature flags for user
AI agents call tracking.feature_flag_eval to retrieve information from MCP Fullstack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Feature flag evaluation is a read-only operation that queries configuration data to determine which features are enabled for a given user. It has no side effects, does not modify state, and poses minimal risk. This fits the 'Read' category as it retrieves data without causing any changes.
From the tool's definition Tool name 'tracking.feature_flag_eval' and description 'Evaluate feature flags for user' indicate a query/lookup operation that retrieves the current state of feature flags without modifying them.
Attacks that exploit this kind of access
Evaluate feature flags for user. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for tracking.feature_flag_eval: 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 MCP Fullstack. Nothing to install.
tracking.feature_flag_eval 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 tracking.feature_flag_eval 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 tracking.feature_flag_eval. 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.
tracking.feature_flag_eval is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →