Add a new field to a collection. Specify field type, interface, and constraints. Example: {collection:
AI agents use create_field 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.
The tool modifies data structure reversibly by adding a field to a collection. This is a Write operation (creates new schema elements) rather than Read (no data retrieval), Execute (not running arbitrary code), Destructive (changes are reversible via field deletion), or Financial (no financial impact).
From the tool's definition "Add a new field to a collection" - this creates/modifies the database schema by introducing a new field with configurable properties (field type, interface, constraints).
Attacks that exploit this kind of access
Add a new field to a collection. Specify field type, interface, and constraints. Example: {collection:. 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 create_field: 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.
create_field 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 create_field 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 create_field. 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.
create_field is provided by the Directus MCP Server MCP server (skeyelab/directus-mcp-server). 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 →