Knowi MCP Server

Connect Claude Code, Claude Desktop, Cursor, or any MCP-compatible AI client to [Knowi](https://www.knowi.com). Query your data, create dashboards

Local serverstdioGo

What is the Knowi MCP MCP server?

Connect Claude Code, Claude Desktop, Cursor, or any MCP-compatible AI client to Knowi. Query your data, create dashboards, manage reports, and more — in natural language, directly from your AI assistant. That is what the knowi mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • knowi_do — Execute any Knowi operation via natural language
  • knowi_ask — Ask a data question — finds the dataset, generates a query, returns results
  • knowi_search — Search across all dashboards, widgets, datasets, and reports
  • knowi_list_dashboards — List all accessible dashboards
  • knowi_get_data — Retrieve data rows from a widget or dataset
  • knowi_push_data — Push data rows to a dataset (creates it if it doesn't exist)
  • knowi_get_details — Get full metadata for any asset
  • knowi_find_widget — Find widgets by name
  • knowi_create_datasource — Create a new datasource connection
  • knowi_create_query — Create and run a query against a datasource
  • knowi_create_widget — Create a new chart or visualization
  • knowi_update_widget — Update an existing widget

What it needs from you

Configuration is passed through the environment: YOUR_MCP_TOKEN, YOUR_NEW_TOKEN, YOUR_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Knowi account with AI Agents enabled (Settings → AI Settings) - Claude Code CLI, Claude Desktop, or any MCP-compatible client ---

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Knowi MCP's toolset — knowi_do, knowi_ask, knowi_search and 11 more — is a fair guide to whether it matches your workflow. It is maintained by cloud9charts; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Knowi MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
knowi_doExecute any Knowi operation via natural language
knowi_askAsk a data question — finds the dataset, generates a query, returns results
knowi_searchSearch across all dashboards, widgets, datasets, and reports
knowi_list_dashboardsList all accessible dashboards
knowi_get_dataRetrieve data rows from a widget or dataset
knowi_push_dataPush data rows to a dataset (creates it if it doesn't exist)
knowi_get_detailsGet full metadata for any asset
knowi_find_widgetFind widgets by name
knowi_create_datasourceCreate a new datasource connection
knowi_create_queryCreate and run a query against a datasource
knowi_create_widgetCreate a new chart or visualization
knowi_update_widgetUpdate an existing widget
knowi_create_reportCreate a scheduled report
knowi_create_alertCreate a data alert

How to install the Knowi MCP MCP server

{
  "mcpServers": {
    "knowi": {
      "type": "streamable-http",
      "url": "https://your-instance.knowi.com/api/2.0/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_TOKEN"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Knowi account with AI Agents enabled (Settings → AI Settings) - Claude Code CLI, Claude Desktop, or any MCP-compatible client ---
VariableDescriptionRequired
YOUR_MCP_TOKENCredential the server authenticates with.Yes
YOUR_NEW_TOKENCredential the server authenticates with.Yes
YOUR_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Knowi MCP to knowi do.
  • Use Knowi MCP to knowi ask.
  • Use Knowi MCP to knowi search.

Frequently asked questions

It connects Knowi MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (knowi_do, knowi_ask, knowi_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Knowi MCP directly.