query_single_file
AI agents call query_single_file to retrieve information from Codesearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries code from a single file without modifying, deleting, or executing anything. It fits the Read category: retrieves data with no side effects. Severity is low because unauthorized code access, while a concern, does not directly damage systems or data compared to write/execute/destructive operations.
From the tool's definition Tool name 'query_single_file' and server context indicate querying/retrieving code from a monorepo. Server description explicitly states tools expose results for querying the codebase.
Attacks that exploit this kind of access
query_single_file. It is categorised as a Read tool in the Codesearch MCP Server, which means it retrieves data without modifying state.
Register the Codesearch MCP server in PolicyLayer and add a rule for query_single_file: 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 Codesearch. Nothing to install.
query_single_file 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_single_file 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_single_file. 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_single_file is provided by the Codesearch MCP server (microsoft/tscodesearch). 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 →