AI agents call debugpy_session_status to retrieve information from Debugpy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
debugpy_session_status queries and returns read-only debugging session state information. It performs no mutations, code execution, or external operations. While it provides internal debugging context about an attached Python process, misuse carries minimal risk since it only reads current session state without triggering execution or modifications. This aligns with the 'Read' category for data retrieval operations.
From the tool's definition Tool description states 'Return the current state' — a purely informational query operation that retrieves debugging session metadata (connection status, breakpoint list, stopped position, mappings) with no modification or side effects.
Attacks that exploit this kind of access
Return the current state of a DAP session: connection, stopped position, breakpoints, mappings. It is categorised as a Read tool in the Debugpy MCP Server, which means it retrieves data without modifying state.
Register the Debugpy MCP server in PolicyLayer and add a rule for debugpy_session_status: 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 Debugpy. Nothing to install.
debugpy_session_status 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 debugpy_session_status 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 debugpy_session_status. 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.
debugpy_session_status is provided by the Debugpy MCP server (will-garrett/debugpy-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 →