AI agents use gwanjong_assets to create or update resources in Gwanjong — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gwanjong environment.
This tool manages an asset library with reversible create/modify operations (save). While it includes read operations (search, list, use), the ability to save new assets or modify the library elevates it to Write category.
From the tool's definition Tool description specifies action: save, search, list, use. The 'save' action creates or stores assets in a library; 'search', 'list', and 'use' are read-like operations. The presence of a save/create capability qualifies this as Write rather than Read.
Attacks that exploit this kind of access
Asset library. action: save, search, list, use. It is categorised as a Write tool in the Gwanjong MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gwanjong MCP server in PolicyLayer and add a rule for gwanjong_assets: 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 Gwanjong. Nothing to install.
gwanjong_assets 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 gwanjong_assets 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 gwanjong_assets. 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.
gwanjong_assets is provided by the Gwanjong MCP server (sonaiengine/gwanjong-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 →