AI agents call list_errors to retrieve information from Bugsnag MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters existing error records from Bugsnag for investigation purposes. It has no side effects, cannot modify data, execute code, or trigger external operations. It is purely informational, fitting the 'Read' category for data retrieval tools.
From the tool's definition Tool name 'list_errors' and description 'List errors in a project with filtering options' indicate retrieval and querying of error data with no modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access list_errors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bugsnag MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_errors:
{
"version": "1",
"default": "deny",
"tools": {
"list_errors": {}
}
}list_errors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List errors in a project with filtering options. It is categorised as a Read tool in the Bugsnag MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bugsnag MCP Server MCP server in PolicyLayer and add a rule for list_errors: 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 Bugsnag MCP Server. Nothing to install.
list_errors 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 list_errors 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 list_errors. 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.
list_errors is provided by the Bugsnag MCP Server MCP server (tgeselle/bugsnag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bugsnag MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 Bugsnag MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.