AI agents use konsulto_create_asset to create or update resources in Konsulto — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Konsulto environment.
The tool creates a new asset record in an audit management platform. This is reversible data modification (assets can typically be deleted or modified later), placing it in the Write category. Severity is medium because creating assets in a security audit platform could lead to audit inaccuracies or scope pollution if misused, but it does not irreversibly destroy data, execute code, or move money.
From the tool's definition Tool name 'konsulto_create_asset' and description 'Create a new asset in the active audit' indicate data creation. The description is incomplete ('Use when a scan or evidence' cuts off), but the verb 'Create' clearly indicates Write semantics.
Attacks that exploit this kind of access
Create a new asset in the active audit. Use when a scan or evidence. It is categorised as a Write tool in the Konsulto MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Konsulto MCP server in PolicyLayer and add a rule for konsulto_create_asset: 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 Konsulto. Nothing to install.
konsulto_create_asset 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 konsulto_create_asset 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 konsulto_create_asset. 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.
konsulto_create_asset is provided by the Konsulto MCP server (konsulto/konsulto-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 →