AI agents call sessions_state to retrieve information from Debug-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves state information from an existing debug session (e.g., current line, variable values, breakpoint status). It performs no modifications, code execution, or side effects. It is analogous to inspection/query operations like 'get' or 'fetch', placing it squarely in the Read category.
From the tool's definition Tool description states it 'Get[s] the current state of a debug session' - a pure query operation that retrieves information about an active debugging session without modifying or executing anything.
Attacks that exploit this kind of access
Get the current state of a debug session. It is categorised as a Read tool in the Debug-MCP MCP Server, which means it retrieves data without modifying state.
Register the Debug- MCP server in PolicyLayer and add a rule for sessions_state: 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 Debug-MCP. Nothing to install.
sessions_state 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 sessions_state 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 sessions_state. 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.
sessions_state is provided by the Debug- MCP server (kaina3/debug-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 →