Query application exceptions and errors
AI agents call azure_exceptions to retrieve information from MCP Container Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries application exceptions and error data, which is fundamentally a retrieval operation with no side effects. It follows the pattern of sibling read tools (azure_traces, azure_metrics, azure_requests, azure_dependencies) that query cloud application telemetry. No data is created, modified, deleted, executed, or financial transactions are performed.
From the tool's definition Tool name 'azure_exceptions' and description 'Query application exceptions and errors' indicate a read-only operation that retrieves and filters data from Azure Application Insights without modifying any state.
Attacks that exploit this kind of access
Query application exceptions and errors. It is categorised as a Read tool in the MCP Container Tools MCP Server, which means it retrieves data without modifying state.
Register the MCP Container Tools MCP server in PolicyLayer and add a rule for azure_exceptions: 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 Container Tools. Nothing to install.
azure_exceptions 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 azure_exceptions 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 azure_exceptions. 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.
azure_exceptions is provided by the MCP Container Tools MCP server (simseksem/mcp-container-tools). 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 →