Get recent failed tool calls with error details
AI agents call selfheal_recent_errors to retrieve information from SelfHeal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents error logs and diagnostic information about past failures. It performs no side effects, creates no resources, executes no code, and deletes nothing. It is a pure read operation for observability and monitoring purposes, typical of debugging and health-check utilities.
From the tool's definition Tool name 'selfheal_recent_errors' and description 'Get recent failed tool calls with error details' indicate a retrieval operation that queries historical error data without modifying or executing anything.
Attacks that exploit this kind of access
Get recent failed tool calls with error details. It is categorised as a Read tool in the SelfHeal MCP MCP Server, which means it retrieves data without modifying state.
Register the SelfHeal MCP server in PolicyLayer and add a rule for selfheal_recent_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 SelfHeal MCP. Nothing to install.
selfheal_recent_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 selfheal_recent_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 selfheal_recent_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.
selfheal_recent_errors is provided by the SelfHeal MCP server (selfheal-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 →