# io.github.Conv-AI/convai-analytics-mcp

Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.2.5
- **Author:** io.github.Conv-AI
- **License:** Unknown
- **npm:** @convai/analytics-mcp
- **Source:** https://github.com/Conv-AI/convai-analytics
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 114 days — stale; the grade is a claim about the present made from dated evidence

## Security scan

- **Status:** clean
- **Scanned:** 2026-06-13T09:11:11.868Z
- **Version scanned:** 0.2.5
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `why_was_this_session_slow`
- `aggregate_latency_distribution`
- `p95_latency_trend`
- `component_bottlenecks`
- `trace_explanation`
- `error_rate_trends`
- `provider_comparison`
- `usage_summary`
- `get_summary`
- `get_metrics_catalog`
- `list_sessions`
- `get_session_timeline`
- `get_interaction_trace`
- `get_first_response_summary`
- `get_first_response_timeseries`
- `get_first_response_breakdown`
- `get_first_response_markers`
- `get_first_response_settings`
- `get_interaction_first_response`
- `get_p95_latency_over_time`
- `get_latency_percentile_series`
- `get_latency_percentile_chart`
- `get_latency_threshold_chart`
- `get_latency_heatmap_chart`
- `get_component_latency_breakdown`
- `generate_component_latency_chart`
- `find_component_latency_bottlenecks`
- `generate_interaction_waterfall`
- `explain_slow_session`
- `get_error_trend`
- `generate_error_trend_chart`
- `get_error_breakdown`
- `generate_error_breakdown_chart`
- `get_dropped_error_persist_trend`
- `generate_dropped_error_persist_chart`
- `generate_reliability_summary_chart`
- `generate_reliability_trends_chart`
- `get_usage_trends`
- `generate_usage_trends_chart`
- `get_character_usage_leaderboard`

## Install

**Verdict: review** — Installable, but 1 thing to check first: The last scan is 114 days old — the evidence behind this verdict is dated.
**Cautions** (coverage gaps and advisories — never blocking)
- The last scan is 114 days old — the evidence behind this verdict is dated.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"analytics\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@convai/analytics-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Moderate to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: privileged tools; runs on your machine.
- Floor 23, ceiling 41 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.Conv-AI%2Fconvai-analytics-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/io.github.Conv-AI%2Fconvai-analytics-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.Conv-AI%2Fconvai-analytics-mcp
- HTML page: https://forgeregistry.com/registry/io.github.Conv-AI%2Fconvai-analytics-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.