MCP.so
Sign In
Servers

Knowi

@cloud9charts

Connect Claude Code, Claude Desktop, and any MCP-compatible AI client to Knowi

Overview

What is Knowi?

Knowi is an MCP server built into the Knowi analytics platform. It lets Claude Code, Claude Desktop, Cursor, or any MCP-compatible AI client query data, create dashboards, manage reports, and more using natural language. No separate installation is required.

How to use Knowi?

Generate an MCP token in Knowi (Settings → AI Settings → MCP Token), then configure your AI client. For Claude Code, run claude mcp add knowi https://your-instance.knowi.com/api/2.0/mcp --transport http --header "Authorization: Bearer YOUR_MCP_TOKEN". For Claude Desktop, edit claude_desktop_config.json with the appropriate URL and token, then restart the desktop app. Verify by asking “What Knowi tools are available?”

Key features of Knowi

  • Built directly into Knowi; no separate server installation
  • AI‑powered tools: knowi_do, knowi_ask, knowi_search
  • Deterministic tools: list dashboards, get/push data, create queries, widgets, reports, alerts
  • Supports file import (CSV, Excel) and document ingestion for AI Q&A
  • Token management with one token per user and easy rotation
  • Security: scoped credentials, authorization on every request, prompt injection protection, destructive operation safeguards, data truncation

Use cases of Knowi

  • Ask natural‑language questions about your data (e.g., “top customers by revenue last month”)
  • Create and update dashboards, widgets, and reports via voice or chat
  • Set up scheduled email reports and data alerts
  • Import files or ingest documents to enable AI querying against unstructured content
  • Export dashboards or widget data as PDF or CSV

FAQ from Knowi

How do I generate an MCP token?

Go to Settings → AI Settings → MCP Token, choose an expiry, and click Generate Token. Copy the token immediately—it is shown only once.

How do I connect Knowi to Claude Code?

Use the command claude mcp add knowi https://your-instance.knowi.com/api/2.0/mcp --transport http --header "Authorization: Bearer YOUR_MCP_TOKEN". Replace the URL with your Knowi instance (use https://www.knowi.com for cloud accounts).

Is there any data flow concern when using Knowi MCP?

Yes, when an AI client calls a Knowi MCP tool, the response (data rows, metadata, insights) is returned to the client and processed on its infrastructure (e.g., Anthropic’s). For maximum data isolation, use Knowi’s in‑product AI agents instead of MCP.

What security features does Knowi MCP include?

MCP tokens are scoped to MCP endpoints only. Every request checks the user’s permissions. AI‑powered tools scan for prompt injection patterns. Destructive operations require the explicit knowi_delete tool with a confirm: true parameter. knowi_get_data and knowi_ask return at most 100 rows by default.

What are the requirements to use Knowi MCP?

A Knowi account with AI Agents enabled (Settings → AI Settings) and an MCP‑compatible client such as Claude Code, Claude Desktop, or Cursor.

More from Other