AI agents use talon_createKnowledge to create or update resources in Talon MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Talon MCP environment.
This tool creates new knowledge documents within the Talon framework, which is a reversible write operation. It does not execute arbitrary code (that would be Execute), does not delete data (not Destructive), and does not involve financial transactions.
From the tool's definition Tool name 'talon_createKnowledge' and description 'Create a new Talon knowledge document' indicate data creation. The Talon framework is an accessibility tool that manages configuration and knowledge documents.
Attacks that exploit this kind of access
Create a new Talon knowledge document. It is categorised as a Write tool in the Talon MCP 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 talon_createKnowledge: 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 MCP. Nothing to install.
talon_createKnowledge 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 talon_createKnowledge 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 talon_createKnowledge. 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.
talon_createKnowledge is provided by the Talon MCP server (trillium/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 →