AI agents invoke session_create to trigger actions in Rr. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Creating a new replay session initiates an external debugging process (rr replay session), which involves spawning processes and setting up execution environments. This is an Execute-category action as it triggers external operations. The severity is high because it starts a new debugging process with reverse execution capabilities, which could be misused to introspect sensitive program state.
From the tool's definition Create a new replay session for debugging a specific
Attacks that exploit this kind of access
Create a new replay session for debugging a specific. It is categorised as a Execute tool in the Rr MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rr MCP server in PolicyLayer and add a rule for session_create: 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.
session_create is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the session_create 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 session_create. 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.
session_create 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.
session_create is one line of Rr's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →