get_source_code_advanced
AI agents call get_source_code_advanced to retrieve information from RAG Document Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description reducing confidence, the tool name and sibling context strongly indicate this retrieves or queries source code data without modifying it. Severity is medium because source code access can expose proprietary or sensitive information, but it remains a read-only operation with no destructive or execution capability.
From the tool's definition Tool name 'get_source_code_advanced' indicates source code retrieval. Sibling tool 'get_source_code' is clearly a Read operation (retrieves data with no side effects).
Attacks that exploit this kind of access
get_source_code_advanced. It is categorised as a Read tool in the RAG Document Server MCP Server, which means it retrieves data without modifying state.
Register the RAG Document Server MCP server in PolicyLayer and add a rule for get_source_code_advanced: 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 RAG Document Server. Nothing to install.
get_source_code_advanced 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 get_source_code_advanced 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 get_source_code_advanced. 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.
get_source_code_advanced is provided by the RAG Document Server MCP server (jaimeferj/mcp-rag-docs). 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 →