AI agents call get_error_history to retrieve information from Pigeon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical error data from a database for debugging purposes. It is a read-only query operation with no destructive, financial, or execution capabilities. The severity is low because error logs typically contain non-sensitive debugging information, and querying them has no side effects on the system state.
From the tool's definition Tool name 'get_error_history' and description 'Query the on-disk error history' indicates retrieval of stored error logs without modification. No deletion, creation, execution, or side effects mentioned.
Attacks that exploit this kind of access
Query the on-disk error history (PIGEON_DB). Spans restarts and goes beyond the. It is categorised as a Read tool in the Pigeon MCP Server, which means it retrieves data without modifying state.
Register the Pigeon MCP server in PolicyLayer and add a rule for get_error_history: 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 Pigeon. Nothing to install.
get_error_history 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_error_history 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_error_history. 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_error_history is provided by the Pigeon MCP server (pepperonas/pigeon). 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 →