Get a specific feature flag by ID
AI agents call getFeatureFlag to retrieve information from Bucketeer MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a specific feature flag's configuration by ID. It performs a query operation that does not modify, delete, or execute any code. The lack of mutation and its read-only nature place it firmly in the Read category. Severity is low as feature flag configurations are typically non-sensitive metadata, and retrieval alone poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'getFeatureFlag' and description 'Get a specific feature flag by ID' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a specific feature flag by ID. It is categorised as a Read tool in the Bucketeer MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bucketeer MCP Server MCP server in PolicyLayer and add a rule for getFeatureFlag: 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 Bucketeer MCP Server. Nothing to install.
getFeatureFlag 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 getFeatureFlag 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 getFeatureFlag. 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.
getFeatureFlag is provided by the Bucketeer MCP Server MCP server (nnnkkk7/bucketeer-mcp). 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 →