awslabs.cloudwatch-appsignals-mcp-server 0.1.9__py3-none-any.whl → 0.1.11__py3-none-any.whl

awslabs/cloudwatch_appsignals_mcp_server/trace_tools.py

@@ -402,6 +402,26 @@ async def query_sampled_traces(
                 return obj.isoformat()
             return obj
 
+        # Helper function to extract fault message from root causes for deduplication
+        def get_fault_message(trace_data):
+            """Extract fault message from a trace for deduplication.
+
+            Only checks FaultRootCauses (5xx server errors) since this is the primary
+            use case for root cause investigation. Traces without fault messages are
+            not deduplicated.
+            """
+            # Only check FaultRootCauses for deduplication
+            root_causes = trace_data.get('FaultRootCauses', [])
+            if root_causes:
+                for cause in root_causes:
+                    services = cause.get('Services', [])
+                    for service in services:
+                        exceptions = service.get('Exceptions', [])
+                        if exceptions and exceptions[0].get('Message'):
+                            return exceptions[0].get('Message')
+            return None
+
+        # Build trace summaries (original format)
         trace_summaries = []
         for trace in traces:
             # Create a simplified trace data structure to reduce size
@@ -417,17 +437,11 @@ async def query_sampled_traces(
 
             # Only include root causes if they exist (to save space)
             if trace.get('ErrorRootCauses'):
-                trace_data['ErrorRootCauses'] = trace.get('ErrorRootCauses', [])[
-                    :3
-                ]  # Limit to first 3
+                trace_data['ErrorRootCauses'] = trace.get('ErrorRootCauses', [])[:3]
             if trace.get('FaultRootCauses'):
-                trace_data['FaultRootCauses'] = trace.get('FaultRootCauses', [])[
-                    :3
-                ]  # Limit to first 3
+                trace_data['FaultRootCauses'] = trace.get('FaultRootCauses', [])[:3]
             if trace.get('ResponseTimeRootCauses'):
-                trace_data['ResponseTimeRootCauses'] = trace.get('ResponseTimeRootCauses', [])[
-                    :3
-                ]  # Limit to first 3
+                trace_data['ResponseTimeRootCauses'] = trace.get('ResponseTimeRootCauses', [])[:3]
 
             # Include limited annotations for key operations
             annotations = trace.get('Annotations', {})
@@ -447,15 +461,50 @@ async def query_sampled_traces(
             # Convert any datetime objects to ISO format strings
             for key, value in trace_data.items():
                 trace_data[key] = convert_datetime(value)
+
             trace_summaries.append(trace_data)
 
+        # Deduplicate trace summaries by fault message
+        seen_faults = {}
+        deduped_trace_summaries = []
+
+        for trace_summary in trace_summaries:
+            # Check if this trace has an error
+            has_issues = (
+                trace_summary.get('HasError')
+                or trace_summary.get('HasFault')
+                or trace_summary.get('HasThrottle')
+            )
+
+            if not has_issues:
+                # Always include healthy traces
+                deduped_trace_summaries.append(trace_summary)
+                continue
+
+            # Extract fault message for deduplication (only checks FaultRootCauses)
+            fault_msg = get_fault_message(trace_summary)
+
+            if fault_msg and fault_msg in seen_faults:
+                # Skip this trace - we already have one with the same fault message
+                seen_faults[fault_msg]['count'] += 1
+                logger.debug(
+                    f'Skipping duplicate trace {trace_summary.get("Id")} - fault message already seen: {fault_msg[:100]}...'
+                )
+                continue
+            else:
+                # First time seeing this fault (or no fault message) - include it
+                deduped_trace_summaries.append(trace_summary)
+                if fault_msg:
+                    seen_faults[fault_msg] = {'count': 1}
+
         # Check transaction search status
         is_tx_search_enabled, tx_destination, tx_status = check_transaction_search_enabled(region)
 
+        # Build response with original format but deduplicated traces
         result_data = {
-            'TraceSummaries': trace_summaries,
-            'TraceCount': len(trace_summaries),
-            'Message': f'Retrieved {len(trace_summaries)} traces (limited to prevent size issues)',
+            'TraceSummaries': deduped_trace_summaries,
+            'TraceCount': len(deduped_trace_summaries),
+            'Message': f'Retrieved {len(deduped_trace_summaries)} unique traces from {len(trace_summaries)} total (deduplicated by fault message)',
             'SamplingNote': "⚠️ This data is from X-Ray's 5% sampling. Results may not show all errors or issues.",
             'TransactionSearchStatus': {
                 'enabled': is_tx_search_enabled,
@@ -467,9 +516,18 @@ async def query_sampled_traces(
             },
         }
 
+        # Add dedup stats if we actually deduped anything
+        if len(deduped_trace_summaries) < len(trace_summaries):
+            duplicates_removed = len(trace_summaries) - len(deduped_trace_summaries)
+            result_data['DeduplicationStats'] = {
+                'OriginalTraceCount': len(trace_summaries),
+                'DuplicatesRemoved': duplicates_removed,
+                'UniqueFaultMessages': len(seen_faults),
+            }
+
         elapsed_time = timer() - start_time_perf
         logger.info(
-            f'query_sampled_traces completed in {elapsed_time:.3f}s - retrieved {len(trace_summaries)} traces'
+            f'query_sampled_traces completed in {elapsed_time:.3f}s - retrieved {len(deduped_trace_summaries)} unique traces from {len(trace_summaries)} total'
         )
         return json.dumps(result_data, indent=2)
 

{awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info → awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: awslabs.cloudwatch-appsignals-mcp-server
-Version: 0.1.9
+Version: 0.1.11
 Summary: An AWS Labs Model Context Protocol (MCP) server for AWS Application Signals
 Project-URL: Homepage, https://awslabs.github.io/mcp/
 Project-URL: Documentation, https://awslabs.github.io/mcp/servers/cloudwatch-appsignals-mcp-server/
@@ -181,7 +181,35 @@ FILTER attributes.aws.local.service = "payment-service" and attributes.aws.local
 - `duration > 5` - Find slow requests (over 5 seconds)
 - `annotation[aws.local.operation]="GET /api/orders"` - Filter by specific operation
 
-#### 12. **`list_slis`** - Legacy SLI Status Report (Specialized Tool)
+#### 12. **`analyze_canary_failures`** - Comprehensive Canary Failure Analysis
+**Deep dive into CloudWatch Synthetics canary failures with root cause identification**
+
+- Comprehensive canary failure analysis with deep dive into issues
+- Analyze historical patterns and specific incident details
+- Get comprehensive artifact analysis including logs, screenshots, and HAR files
+- Receive actionable recommendations based on AWS debugging methodology
+- Correlate canary failures with Application Signals telemetry data
+- Identify performance degradation and availability issues across service dependencies
+
+**Key Features:**
+- **Failure Pattern Analysis**: Identifies recurring failure modes and temporal patterns
+- **Artifact Deep Dive**: Analyzes canary logs, screenshots, and network traces for root causes
+- **Service Correlation**: Links canary failures to upstream/downstream service issues using Application Signals
+- **Performance Insights**: Detects latency spikes, fault rates, and connection issues
+- **Actionable Remediation**: Provides specific steps based on AWS operational best practices
+- **IAM Analysis**: Validates IAM roles and permissions for common canary access issues
+- **Backend Service Integration**: Correlates canary failures with backend service errors and exceptions
+
+**Common Use Cases:**
+- Incident Response: Rapid diagnosis of canary failures during outages
+- Performance Investigation: Understanding latency and availability degradation
+- Dependency Analysis: Identifying which services are causing canary failures
+- Historical Trending: Analyzing failure patterns over time for proactive improvements
+- Root Cause Analysis: Deep dive into specific failure scenarios with full context
+- Infrastructure Issues: Diagnose S3 access, VPC connectivity, and browser target problems
+- Backend Service Debugging: Identify application code issues affecting canary success
+
+#### 13. **`list_slis`** - Legacy SLI Status Report (Specialized Tool)
 **Use `audit_services()` as the PRIMARY tool for service auditing**
 
 - Basic report showing summary counts (total, healthy, breached, insufficient data)
@@ -526,6 +554,68 @@ Found 8 services being monitored:
 3. Review payment-api-service timeout configurations
 ```
 
+### Example 6: Canary Failure Analysis and Root Cause Investigation
+```
+User: "My Pet Clinic canaries are failing. Can you help me diagnose the issues?"
+Assistant: I'll analyze your Pet Clinic canaries to identify the root causes of failures.
+
+[Uses analyze_canary_failures for comprehensive canary analysis]
+
+analyze_canary_failures(canary_name="pc-visit-vet")
+analyze_canary_failures(canary_name="pc-add-visit")
+analyze_canary_failures(canary_name="webapp-erorrpagecanary")
+
+🔍 CANARY FAILURE ANALYSIS RESULTS:
+
+🔴 CRITICAL ISSUES IDENTIFIED:
+
+**pc-visit-vet canary:**
+• Root Cause: S3 bucket access issue
+• Error Pattern: Exit status 127, "No such file or directory"
+• Failure Count: 5 consecutive failures
+• IAM Analysis: ✅ Role exists but S3 bucket ARN patterns incorrect in policies
+
+**pc-add-visit canary:**
+• Root Cause: Selector timeout + backend service errors
+• Error Pattern: 30000ms timeout waiting for UI element + MissingFormatArgumentException
+• Backend Issue: Format specifier '% o' error in BedrockRuntimeV1Service.invokeTitanModel()
+• Performance: 34 second average response time, 0% success rate
+
+**webapp-erorrpagecanary:**
+• Root Cause: Browser target close during selector wait
+• Error Pattern: "Target closed" waiting for `#jsError` selector
+• Failure Count: 5 consecutive failures with 60000ms connection timeouts
+
+🔍 BACKEND SERVICE CORRELATION:
+• MissingFormatArgumentException detected in Pet Clinic backend
+• Location: org.springframework.samples.petclinic.customers.aws.BedrockRuntimeV1Service.invokeTitanModel (line 75)
+• Impact: Affects multiple canaries testing Pet Clinic functionality
+• 20% fault rate on GET /api/customer/diagnose/owners/{ownerId}/pets/{petId}
+
+🛠️ RECOMMENDED ACTIONS:
+
+**Immediate (Critical):**
+1. Fix S3 bucket ARN patterns in pc-visit-vet IAM policy
+2. Fix format string bug in BedrockRuntimeV1Service: change '% o' to '%s' or correct format
+3. Add VPC permissions to canary IAM roles if Lambda runs in VPC
+
+**Infrastructure (High Priority):**
+4. Investigate browser target stability issues (webapp-erorrpagecanary)
+5. Review canary timeout configurations - consider increasing from 30s to 60s
+6. Implement circuit breaker pattern for external service dependencies
+
+**Monitoring (Medium Priority):**
+7. Add Application Signals monitoring for canary success rates
+8. Set up alerts for consecutive canary failures (>3 failures)
+9. Implement canary health dashboard with real-time status
+
+🎯 EXPECTED OUTCOMES:
+• S3 access fix: Immediate resolution of pc-visit-vet failures
+• Backend service fix: 80%+ improvement in Pet Clinic canary success rates
+• Infrastructure improvements: Reduced browser target close errors
+• Enhanced monitoring: Proactive failure detection and faster resolution
+```
+
 ## Recommended Workflows
 
 ### 🎯 Primary Audit Workflow (Most Common)

awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/RECORD

@@ -0,0 +1,19 @@
+awslabs/__init__.py,sha256=WuqxdDgUZylWNmVoPKiK7qGsTB_G4UmuXIrJ-VBwDew,731
+awslabs/cloudwatch_appsignals_mcp_server/__init__.py,sha256=-03Q_rK9fNWDftPT4JwNlDDVrjN7thel1i8Q5pByG6o,682
+awslabs/cloudwatch_appsignals_mcp_server/audit_presentation_utils.py,sha256=xYJz0I-wdigYKxAaVLjyoMUh2UQpwlZM7sFxfL2pPmw,8923
+awslabs/cloudwatch_appsignals_mcp_server/audit_utils.py,sha256=mcXxVjla0Wnh3ItuSralPFBhRWvhoWLgtvIHcAGJQog,31031
+awslabs/cloudwatch_appsignals_mcp_server/aws_clients.py,sha256=YbUeyz_yz1n5e9EfOYYXSTZNmnkvkVF0iXrByT5aB-A,4726
+awslabs/cloudwatch_appsignals_mcp_server/canary_utils.py,sha256=bymLDQ1kFeNIJwMRcWOLXOd2b0NyWSqmmwMrdXMxqPg,37456
+awslabs/cloudwatch_appsignals_mcp_server/server.py,sha256=ZoYd-UgY7jFOsXLnV5gWTKDzFkmbvF2vpqEnHLgbO5Q,67903
+awslabs/cloudwatch_appsignals_mcp_server/service_audit_utils.py,sha256=i-6emomFio4xsVsb5iRWvOzuHI7vo7WXe7VlLMD-qK8,9659
+awslabs/cloudwatch_appsignals_mcp_server/service_tools.py,sha256=iJnkROnR0FdxEgF0LJb5zYNcD-CCSa9LVXwUqxU1_tI,29093
+awslabs/cloudwatch_appsignals_mcp_server/sli_report_client.py,sha256=LGs7tDLVVa3mbT_maTefwGEA3cl3fNVft9brh3lVTzM,12374
+awslabs/cloudwatch_appsignals_mcp_server/slo_tools.py,sha256=dMLGqeZYHu2adk9uquBGIZkMZStb-puzlI0xtKhxYNI,17824
+awslabs/cloudwatch_appsignals_mcp_server/trace_tools.py,sha256=SMIaxStaJNZOU4GaAFkUiNXrb978bPTlF7MRBRJVEP8,31785
+awslabs/cloudwatch_appsignals_mcp_server/utils.py,sha256=nZBqiCBAUewQft26FVf4IGL4P1b152VAcG9Y7Mh0gZY,5782
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/METADATA,sha256=iXciAJl-rIk4WiFMWy6AQcLGpCdFgKgcjue52r1BkWQ,31858
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/entry_points.txt,sha256=iGwIMLU6AsBawl2Fhqi9GoeWdMGIVtg86-McaaNQqAQ,114
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/licenses/LICENSE,sha256=zE1N4JILDTkSIDtdmqdnKKxKEQh_VdqeoAV2230eNOI,10141
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/licenses/NOTICE,sha256=Pfbul2Ga0IJU2RMZFHC8QwDvNk72WO2XMn9l3390VYs,108
+awslabs_cloudwatch_appsignals_mcp_server-0.1.11.dist-info/RECORD,,

awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/RECORD

@@ -1,18 +0,0 @@
-awslabs/__init__.py,sha256=WuqxdDgUZylWNmVoPKiK7qGsTB_G4UmuXIrJ-VBwDew,731
-awslabs/cloudwatch_appsignals_mcp_server/__init__.py,sha256=cPlKPRqNSL5d4RkWGdDJ_7jay1qZs4ppnntzxDdr4nw,681
-awslabs/cloudwatch_appsignals_mcp_server/audit_presentation_utils.py,sha256=xYJz0I-wdigYKxAaVLjyoMUh2UQpwlZM7sFxfL2pPmw,8923
-awslabs/cloudwatch_appsignals_mcp_server/audit_utils.py,sha256=Mqa8q3MUMpDKRFJQgUoKYikknGO4sBIe2_-0e2BWlCA,30765
-awslabs/cloudwatch_appsignals_mcp_server/aws_clients.py,sha256=I-amnrnVLGv-gAPkEYo-AxvmqktBjpdEuB1pjeTO1Fs,3542
-awslabs/cloudwatch_appsignals_mcp_server/server.py,sha256=nZ_s6lKQBf77Wdy8eyGLYPDmOBGAq1ZNH41BMpdYwQw,41569
-awslabs/cloudwatch_appsignals_mcp_server/service_audit_utils.py,sha256=i-6emomFio4xsVsb5iRWvOzuHI7vo7WXe7VlLMD-qK8,9659
-awslabs/cloudwatch_appsignals_mcp_server/service_tools.py,sha256=iJnkROnR0FdxEgF0LJb5zYNcD-CCSa9LVXwUqxU1_tI,29093
-awslabs/cloudwatch_appsignals_mcp_server/sli_report_client.py,sha256=LGs7tDLVVa3mbT_maTefwGEA3cl3fNVft9brh3lVTzM,12374
-awslabs/cloudwatch_appsignals_mcp_server/slo_tools.py,sha256=dMLGqeZYHu2adk9uquBGIZkMZStb-puzlI0xtKhxYNI,17824
-awslabs/cloudwatch_appsignals_mcp_server/trace_tools.py,sha256=F-vanuK8preiRHyI-EbZoOcxTueycDk-rRRPtjmKg5E,28990
-awslabs/cloudwatch_appsignals_mcp_server/utils.py,sha256=nZBqiCBAUewQft26FVf4IGL4P1b152VAcG9Y7Mh0gZY,5782
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/METADATA,sha256=WQuVsqGbrqcKZp0SA4cPBIGA0fSRRc_UNJ1ueUcjW78,27162
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/entry_points.txt,sha256=iGwIMLU6AsBawl2Fhqi9GoeWdMGIVtg86-McaaNQqAQ,114
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/licenses/LICENSE,sha256=zE1N4JILDTkSIDtdmqdnKKxKEQh_VdqeoAV2230eNOI,10141
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/licenses/NOTICE,sha256=Pfbul2Ga0IJU2RMZFHC8QwDvNk72WO2XMn9l3390VYs,108
-awslabs_cloudwatch_appsignals_mcp_server-0.1.9.dist-info/RECORD,,