AI agents call error_check to retrieve information from Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes error data from a terminal context without executing code, modifying state, or creating side effects. It functions as a diagnostic and logging mechanism, consistent with the Read category. Severity is low because error inspection poses minimal risk even if misused by an agent.
From the tool's definition Tool is described as 'Diagnose and track terminal errors' — it reads error information and performs diagnostics, with no indication of modification, deletion, or execution of commands. The verb 'diagnose' and 'track' are monitoring/inspection actions.
Attacks that exploit this kind of access
Diagnose and track terminal errors.\n. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for error_check: 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 Context. Nothing to install.
error_check 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 error_check 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 error_check. 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.
error_check is provided by the Context MCP server (vibhasdutta/context-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 →