Convai Analytics

Name: Convai Analytics
Author: Conv-AI

by Conv-AIversion 0.2.5i★ –iRuns on your computer

Registry nameio.github.Conv-AI/convai-analytics-mcp

Install

Overview

Description from the maker (original English)

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

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Marketing & social media
You need to fill in: CONVAI_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: CONVAI_API_KEY, CONVAI_ANALYTICS_BASE_URL

Values marked secret are keys to your account. Never share them or paste them into a chat.

You need

npmNode.js installed (for the npx command)

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "convai-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "@convai/analytics-mcp"
      ],
      "env": {
        "CONVAI_API_KEY": "your-value",
        "CONVAI_ANALYTICS_BASE_URL": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add convai-analytics --env CONVAI_API_KEY=your-value --env CONVAI_ANALYTICS_BASE_URL=your-value -- npx -y @convai/analytics-mcp

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "convai-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "@convai/analytics-mcp"
      ],
      "env": {
        "CONVAI_API_KEY": "your-value",
        "CONVAI_ANALYTICS_BASE_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "convai-analytics": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@convai/analytics-mcp"
      ],
      "env": {
        "CONVAI_API_KEY": "your-value",
        "CONVAI_ANALYTICS_BASE_URL": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

CONVAI_API_KEY secret required env
Convai API key for the account to query.
CONVAI_ANALYTICS_BASE_URL env
Optional analytics API base URL override.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account Conv-AI, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Marketing & social mediai

More stars than 0% of the other 2987 servers in this category
Published to the registry more recently than 9% of the other 2987 servers in this category
Basic checks equal to or better than 100% of the other 2987 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Convai Analytics safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: CONVAI_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.5) reached the registry 6 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

MCP YouTube Transcript

by jkawamoto

An MCP server retrieving transcripts of YouTube videos

Runs on your computer★ 495MITUpdated 10 days ago

Install

Google Analytics MCP

by surendranb

GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.

Runs on your computer★ 244MITUpdated 10 days ago

Install

BibiGPT YouTube Video Summarizer

by JimmyLv

AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.

Runs in the cloud★ 137MITUpdated 10 days ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@convai/analytics-mcp

Local stdio MCP server for Convai Analytics.

This package is the recommended agent interface for Convai Analytics. It lets MCP-capable agents answer questions about your Convai sessions, latency, reliability, usage, and provider/model performance without writing custom SDK scripts. It wraps the public @convai/analytics TypeScript SDK, uses CONVAI_API_KEY, and returns structured JSON plus Vega-Lite chart specs.

Package: @convai/analytics-mcp

Official MCP Registry name: io.github.Conv-AI/convai-analytics-mcp

Install And Run

export CONVAI_API_KEY="ck_live_your_key_here"

npx -y @convai/analytics-mcp@latest

Optional:

export CONVAI_ANALYTICS_BASE_URL="https://analytics-api.convai.com/v1/analytics"

Leave CONVAI_ANALYTICS_BASE_URL unset for production. Do not put the API key in source code, committed MCP config, screenshots, or logs.

After adding or changing MCP config, restart Claude Desktop, Claude Code, Cursor, Codex, or your MCP host so it reloads the server command and CONVAI_API_KEY.

Claude Desktop

"mcpServers": { "convai-analytics": { "command": "npx", "args": ["-y", "@convai/analytics-mcp@latest"], "env": { "CONVAI_API_KEY": "ck_live_your_key_here" } } } }

After saving this config, quit and reopen Claude Desktop so it starts the new MCP server.

Cursor / Codex-Compatible MCP Clients

Use the same stdio command:

"command": "npx", "args": ["-y", "@convai/analytics-mcp@latest"], "env": { "CONVAI_API_KEY": "ck_live_your_key_here" } }

For Claude Code, Cursor, Codex-compatible clients, and other stdio MCP hosts, restart the client or start a new session after adding or changing MCP config.

Security Model

The server is customer-facing and public-safe by design:

It only calls the public Convai Analytics API through @convai/analytics.
It does not accept account overrides, service credentials, database URLs, or other internal access paths.
Account scoping, plan gating, and quota enforcement stay server-side in the hosted analytics API.
Tool results are sanitized so errors do not echo CONVAI_API_KEY.

Tools

Core and account tools:

get_summary
get_metrics_catalog
list_sessions
get_session_timeline
get_interaction_trace

Latency tools:

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

Reliability tools:

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

These reliability tools use error and dropped-persistence metrics that are available today. If an agent asks for a status distribution, only use group_by=status when the returned rows contain real non-empty status groups; otherwise report that status-tagged aggregate telemetry is not available for that range.

Usage and concurrency tools:

get_usage_trends
generate_usage_trends_chart
get_character_usage_leaderboard
generate_character_usage_chart
generate_session_duration_scatter
estimate_active_session_concurrency
generate_active_session_concurrency_chart
generate_peak_concurrency_chart

Provider and model tools:

get_tts_provider_attribution
generate_tts_provider_chart
get_llm_model_latency
generate_llm_model_latency_chart
compare_providers

Plan-gated advanced tools:

detect_regressions
advanced_query

Plan-gated tools return typed MCP tool errors for 402/403 responses with the required plan in the message.

Prompts

The server exposes prompt templates for common customer questions:

why_was_this_session_slow
aggregate_latency_distribution
p95_latency_trend
component_bottlenecks
trace_explanation
error_rate_trends
provider_comparison
usage_summary

Resources

convai://analytics/docs/concepts
convai://analytics/docs/metrics-reference
convai://analytics/docs/authentication
convai://analytics/catalog

The catalog resource fetches the caller's account catalog when CONVAI_API_KEY is available.

Example Questions

How many interactions and unique end users did I have in the last 30 days?

Break it down by character and generate a usage trend chart.

Show aggregate P50/P95/P99 voice.user_to_bot_latency for production readiness sign-off.

Add a 3000 ms p95 threshold line and summarize the worst buckets.

Explain why session s_123 was slow and generate an interaction waterfall if there is a traceable interaction.

Show reliability trends, errors by component, and dropped error-persistence events.

Estimate active session concurrency and show the peak concurrency chart.

Local Development

From the repo root:

make mcp-install

make mcp-lint make mcp-test make mcp-build make mcp-smoke

Live smoke against production with your own key:

export CONVAI_API_KEY="ck_live_your_key_here"

export CONVAI_ANALYTICS_BASE_URL="https://analytics-api.convai.com/v1/analytics" export CONVAI_ANALYTICS_E2E_RANGE="last_30d" cd packages/mcp npm run e2e:prod

The live smoke accepts empty data for accounts without recent traffic and treats plan-gated 402/403 responses as valid gated results.

Discovery

The canonical MCP registry manifest is server.json. The server is published to npm and the Official MCP Registry. Additional directories and marketplaces such as GitHub MCP Registry, Smithery, Glama, PulseMCP, mcp.so, and Docker MCP Catalog can reference the same package and registry metadata.

Convai Analytics

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Marketing & social mediai

Common questions

Alternatives

MCP YouTube Transcript

Google Analytics MCP

BibiGPT YouTube Video Summarizer

README from the maker

@convai/analytics-mcp

Install And Run

Claude Desktop

Cursor / Codex-Compatible MCP Clients

Security Model

Tools

Prompts

Resources

Example Questions

Local Development

Discovery