Get detailed context about a process crash, including the error message, stack trace, and relevant file paths. Use this when the user mentions a crash or when you need to understand why a process failed.
AI agents call get_crash_context to retrieve information from VibeWatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic information about process failures. It reads and returns existing crash data, error messages, stack traces, and file paths without modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could request excessive crash details but cannot harm systems or data through this read-only operation.
From the tool's definition Tool description: 'Get detailed context about a process crash, including the error message, stack trace, and relevant file paths.' The verb 'Get' and the retrieval-only nature of extracting crash context, error messages, and stack traces indicates this is a…
Attacks that exploit this kind of access
Get detailed context about a process crash, including the error message, stack trace, and relevant file paths. Use this when the user mentions a crash or when you need to understand why a process failed. It is categorised as a Read tool in the VibeWatch MCP Server, which means it retrieves data without modifying state.
Register the VibeWatch MCP server in PolicyLayer and add a rule for get_crash_context: 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 VibeWatch. Nothing to install.
get_crash_context 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_crash_context 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_crash_context. 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_crash_context is provided by the VibeWatch MCP server (krjordan/vibewatch). 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 →