AI agents use kanka_update_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.
This tool creates or modifies data in a reversible manner (PATCH operation), fitting the Write category. It is not Destructive because PATCH updates are reversible and do not permanently erase data. Severity is medium because unintended modifications to campaign entities could disrupt data integrity, but the impact is limited to updates rather than deletions, and changes can be corrected.
From the tool's definition Tool performs 'Partial update (PATCH) on an existing entity' which modifies data reversibly. The description explicitly states it updates existing entities with provided fields.
Attacks that exploit this kind of access
Partial update (PATCH) on an existing entity. Provide only the fields you want to change. The. 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_update_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_update_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_update_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_update_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_update_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 →