AI agents use create_application to create or update resources in Talon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Talon environment.
This tool creates a new application resource, which is a reversible write operation. The severity is medium because creating an application could be misused to establish unauthorized access points or deploy malicious applications within an organization, but the action itself is not irreversible (the application can be deleted) and does not directly move money or execute arbitrary code.
From the tool's definition Tool description states 'Create a new application within an organization' — the word 'Create' indicates data creation.
Attacks that exploit this kind of access
Create a new application within an organization. It is categorised as a Write tool in the Talon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Talon MCP server in PolicyLayer and add a rule for create_application: 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 Talon. Nothing to install.
create_application 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_application 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_application. 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_application is provided by the Talon MCP server (talon-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 →