AI agents use kanka_create_entity to create or update resources in Kanka — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kanka environment.
Creating entities is a reversible write operation that modifies the campaign database by adding new records. While high severity due to the potential for spam or data pollution across 18 different entity types in a user's campaign, it is categorized as Write rather than Execute or Destructive because: (1) the operation is reversible via kanka_delete_entity, (2) it creates data rather than executing arbitrary code,…
From the tool's definition Tool name is kanka_create_entity and description states 'Create a new entity', which creates new data in the campaign system. Server description confirms 'CRUD on all 18 entity types'.
Attacks that exploit this kind of access
Create a new entity. Call kanka_describe_entity_type first to discover the per-type schema for. It is categorised as a Write tool in the Kanka MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kanka MCP server in PolicyLayer and add a rule for kanka_create_entity: 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 Kanka. Nothing to install.
kanka_create_entity 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 kanka_create_entity 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 kanka_create_entity. 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.
kanka_create_entity is provided by the Kanka MCP server (torinvdb/kanka-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 →