Agent Error Propagation Tracker

Agent Error Propagation Tracker MCP Connector for Claude

A+

Trace error chains and calculate system impact in multi-agent environments.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner

This MCP server provides deterministic diagnostic capabilities for multi-agent systems. It identifies the origin of failures by tracing error flows through dependency chains and calculates critical impact metrics like blast radius and error amplification. Use analyze_error_chain to find the root cause of a failure sequence, calculate_impact_metrics to quantify the severity of an incident, and evaluate_resilience to assess how well your agents recover from cascading failures.

error-tracingroot-causemulti-agentreliabilityobservability

3 tools expose this connector's capabilities to your AI agent.

analyze_error_chain

Identifies the specific sequence of errors forming a causal chain and finds the original culprit

calculate_impact_metrics

Quantifies the severity and spread of an error event

evaluate_resilience

Determines how well agents recover from failures and how many are failing due to cascades

See how to talk to your AI agent using Agent Error Propagation Tracker.

Analyze these error logs to find the root cause and the error chain.

The root cause was Agent-A. The error chain is: Agent-A (Timeout) -> Agent-B (Dependency Failure) -> Agent-C (Service Unavailable).

Calculate the impact of the recent failures using a 60 second window.

The incident resulted in 4 correlated errors and consumed 20% of your error budget.

Check the resilience of my agents after the last cascade.

The system detected a cascading failure, but the retry success rate for Agent-B was 100%.

The `analyze_error_chain` tool traverses the dependency graph alongside error timestamps to find the first agent in a causal sequence that failed.

Related Connectors