AI agents call gwanjong_draft to retrieve information from Gwanjong without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only retrieves and returns data (post content, comments, sentiment analysis) for a given opportunity. There are no side effects described — it is a pure read/fetch operation in the scout-draft-strike pipeline, used to gather context before any action is taken.
From the tool's definition Gather full context for a specific opportunity. Returns post, comments, and sentiment analysis.
Attacks that exploit this kind of access
Gather full context for a specific opportunity. Returns post, comments, and sentiment analysis. It is categorised as a Read tool in the Gwanjong MCP Server, which means it retrieves data without modifying state.
Register the Gwanjong MCP server in PolicyLayer and add a rule for gwanjong_draft: 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_draft is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gwanjong_draft 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_draft. 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_draft 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.
gwanjong_draft is one line of Gwanjong's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →