AI agents use kotor_extract_resource to create or update resources in KotorMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KotorMCP environment.
This tool writes data to the filesystem, which is a Write operation. It creates or modifies files on disk. The severity is medium because it can write files to arbitrary locations depending on arguments, but the server context (KOTOR game files) limits the blast radius somewhat. Confidence is slightly reduced because the description is brief and doesn't clarify overwrite behavior or destination path constraints.
From the tool's definition 'write a resolved resource to disk'
Attacks that exploit this kind of access
Use when you need to write a resolved resource to disk. Optional. It is categorised as a Write tool in the KotorMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kotor MCP server in PolicyLayer and add a rule for kotor_extract_resource: 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 KotorMCP. Nothing to install.
kotor_extract_resource 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 kotor_extract_resource 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 kotor_extract_resource. 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.
kotor_extract_resource is provided by the Kotor MCP server (th3w1zard1/kotormcp). 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 →