Everything you get with ContextPulse
See who uses your MCP server, what they are trying to do, whether the work gets done, and what to fix next. All from one line of code.
Tool Analytics
Every call ranked and trended. See which tools get called, how often, and how that shifts week over week. The ones pulling weight and the ones just sitting there both surface immediately.
- Call volume and share per tool
- Trends across any time range
- Break any metric down by tool
Latency & Errors
Know which tool is slow before your users do. Every tool gets a latency and error-rate profile: p50 for typical execution, p95 for the tail that quietly ruins agent sessions.
- p50 and p95 latency per tool
- Error rate trended over time
- Sort tools by failure frequency
Client Attribution
See which AI clients connect. Break down usage by Claude Desktop, Cursor AI, ChatGPT Operator, and custom agents. Understand transport nuances (stdio vs SSE vs HTTP).
- Client version detection
- Transport protocol telemetry
- Multi-client session benchmarking
Workflow Funnels
Measure if agents finish the job. Visualize multi-turn sequences as structured conversion funnels. Detect exactly where an agent gets confused or drops off mid-session.
- Step-by-step drop-off inspection
- Retry loop cost estimation
- Multi-turn goal completion metrics
Incident Alerts
Get notified before an incident spreads. Automatically dispatch webhook payloads and Slack alerts when error rates surge or when tool arguments fail validation continuously.
- Slack channel notifications
- Custom HTTP webhook endpoints
- Dynamic anomaly thresholds
Bounded Redaction
Security is part of the telemetry design. Tokens, API keys, passwords, and sensitive credentials are recursively scrubbed in process memory before transmission.
- Zero raw prompt transmission
- Configurable metadataOnly mode
- Local in-memory string scrubbing
Start measuring your MCP server today
One line of code. Fail-open telemetry. 14-day risk-free trial.