Update an existing flow
AI agents use update_flow to create or update resources in Directus MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Directus MCP Server environment.
This tool modifies existing workflow automation rules in Directus CMS. While not destructive (changes are reversible), it qualifies as Write since it alters existing data. Severity is high because flows in a CMS can automate critical operations (sending emails, creating records, triggering webhooks, etc.), so an unauthorized or erroneous flow modification could have broad downstream effects on system behavior.
From the tool's definition Tool name is 'update_flow' and description states 'Update an existing flow' - this is explicitly a modification operation on existing data (flows).
Attacks that exploit this kind of access
Update an existing flow. It is categorised as a Write tool in the Directus MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Directus MCP Server MCP server in PolicyLayer and add a rule for update_flow: 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 Directus MCP Server. Nothing to install.
update_flow 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_flow 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_flow. 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_flow is provided by the Directus MCP Server MCP server (staminna/mcp-server-claude). 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 →