Get last exception/event information
AI agents call get_exception_info to retrieve information from MCP Debug Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves exception and event information from a debugged process, which is a Read operation (query, inspect). However, severity is rated high because exception information can reveal sensitive details about process internals, memory layouts, and security vulnerabilities.
From the tool's definition Tool name 'get_exception_info' and description 'Get last exception/event information' indicate retrieval of debugging state without modification. The action is read-only—querying exception data from an attached process.
Attacks that exploit this kind of access
Get last exception/event information. It is categorised as a Read tool in the MCP Debug Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Debug Server MCP server in PolicyLayer and add a rule for get_exception_info: 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 MCP Debug Server. Nothing to install.
get_exception_info 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_exception_info 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_exception_info. 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_exception_info is provided by the MCP Debug Server MCP server (nickzer0/mcp-debugserver). 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 →