Query parsed code knowledge. Select
AI agents call code_query to retrieve information from Agent Wiki without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or searches parsed code knowledge without modifying, executing, or deleting any data. It is a straightforward query operation analogous to a search or fetch, placing it firmly in the Read category. The lack of any mention of execution, modification, or deletion, combined with the explicit 'Query' verb, supports low severity and high confidence.
From the tool's definition Tool name is 'code_query' and description states 'Query parsed code knowledge.' The verb 'query' and action of retrieving/selecting knowledge indicates a read-only operation with no side effects.
Attacks that exploit this kind of access
Query parsed code knowledge. Select. It is categorised as a Read tool in the Agent Wiki MCP Server, which means it retrieves data without modifying state.
Register the Agent Wiki MCP server in PolicyLayer and add a rule for code_query: 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 Agent Wiki. Nothing to install.
code_query 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 code_query 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 code_query. 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.
code_query is provided by the Agent Wiki MCP server (xinhuagu/agent-wiki). 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 →