Provides a local MCP server, SDKs, and CLI for querying Convai application telemetry via Convai's hosted Analytics API using a Convai API key. It supports account-scoped analytics reads such as summaries, timeseries, breakdowns, session and interaction inspection, and regression detection.
From the registry: Analyze Convai sessions, latency, reliability, usage, and provider telemetry via API key.
Please install the `convai-analytics-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js 18+** — Node.js 18 or newer is required to run the published MCP server via npx.
- **Create a Convai API key** — Generate a Convai API key for the Convai account whose analytics you want to query. The MCP server requires this key to authenticate to Convai's hosted analytics API.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@convai/analytics-mcp@latest"]
- required environment variables:
- `CONVAI_API_KEY`: Convai API key used to authenticate requests to the analytics API. (example: `<your-convai-api-key>`)
- optional environment variables:
- `CONVAI_ANALYTICS_BASE_URL`: Optional override for the analytics API base URL. Production is the default, so this is usually not needed. (example: `<your-analytics-base-url>`)
Note: Recommended install path is the published local MCP server package `@convai/analytics-mcp`. The README also mentions MCP Registry discovery via `io.github.Conv-AI/convai-analytics-mcp`, but the canonical portable config is the stdio npx command.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CONVAI_API_KEYrequiredConvai API key used to authenticate analytics requests for the account being queried.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.