Search code using SACL bias-aware retrieval with semantic augmentation
AI agents call query_code to retrieve information from SACL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves code with semantic analysis and bias detection. It performs a read-only query operation returning code search results with no side effects on the codebase. The blast radius if misused is minimal—an AI agent could retrieve inappropriate code or sensitive information, but cannot modify, execute, or delete anything.
From the tool's definition Tool name 'query_code' and description 'Search code using SACL bias-aware retrieval with semantic augmentation' indicate a retrieval/search operation.
Attacks that exploit this kind of access
Search code using SACL bias-aware retrieval with semantic augmentation. It is categorised as a Read tool in the SACL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SACL MCP Server MCP server in PolicyLayer and add a rule for query_code: 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 SACL MCP Server. Nothing to install.
query_code 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 query_code 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 query_code. 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.
query_code is provided by the SACL MCP Server MCP server (ulasbilgen/sacl). 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 →