Update a feature flag by key (WRITE).
AI agents use update_feature_flag to create or update resources in Dynatrace SaaS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dynatrace SaaS MCP Server environment.
This tool creates or modifies feature flag data reversibly. While feature flags control application behavior and could have broad impact if misconfigured by an agent, the operation is not inherently destructive (can be reverted), not financial, and does not execute arbitrary code.
From the tool's definition Tool name 'update_feature_flag' and explicit description marking it as '(WRITE)' indicate modification of feature flag configuration state.
Attacks that exploit this kind of access
Update a feature flag by key (WRITE). It is categorised as a Write tool in the Dynatrace SaaS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dynatrace SaaS MCP Server MCP server in PolicyLayer and add a rule for update_feature_flag: 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 Dynatrace SaaS MCP Server. Nothing to install.
update_feature_flag is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_feature_flag 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 update_feature_flag. 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.
update_feature_flag is provided by the Dynatrace SaaS MCP Server MCP server (mnmozi/dynatrace-mcp-saas). 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 →