AI agents call source_path to retrieve information from Rr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves the current debugging context (source file location). It has no side effects, does not modify debugger state, and does not execute code. It belongs in the Read category with low severity since it only exposes debugging metadata that an AI agent would reasonably need during a debugging session.
From the tool's definition Tool name 'source_path' and description 'Get the current source file path and line number' indicate a query operation that retrieves debugging state without modifying any data or triggering side effects.
Attacks that exploit this kind of access
Get the current source file path and line number. It is categorised as a Read tool in the Rr MCP Server, which means it retrieves data without modifying state.
Register the Rr MCP server in PolicyLayer and add a rule for source_path: 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 Rr. Nothing to install.
source_path 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 source_path 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 source_path. 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.
source_path is provided by the Rr MCP server (jnjaeschke/rr-mcp). 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 →