Dataiku MCP

io.github.clssck由 GitHub 帳號 clssck 發布v1.1.1更新於 Oct 27, 2026

MCP server for Dataiku DSS project, flow, and operations APIs.

已驗證STDIO僅桌面開發者工具資料與分析

概覽

AI 產生的概覽

本機 MCP 伺服器,讓助理透過 Dataiku DSS REST API 檢視並操作專案、流程、資料集、配方、作業、情境與資料夾。

可以做什麼
  • 列出、讀取並產生專案流程地圖,包含配方子類型與連線關係
  • 列出、檢視、預覽、下載、建立、更新與刪除資料集與配方
  • 列出、檢視、建置、等待與中止作業,並讀取作業日誌
  • 列出、執行與管理情境,讀取或設定專案變數
  • 瀏覽受管資料夾及其內容,上傳、下載與刪除檔案
  • 推斷連線資訊,列出程式碼環境
適用情境
適合在 Dataiku DSS 中工作、希望助理梳理專案流程、查看資料集結構與預覽、執行或監控建置與情境、管理資料夾與變數而不必切換到 DSS 介面的情況。
執行需求
以 Node.js 20+ 的 npm 套件(dataiku-mcp)透過 stdio 在本機執行。需要 DATAIKU_URL 提供 DSS 實例網址、DATAIKU_API_KEY 提供 DSS API 金鑰;DATAIKU_PROJECT_KEY 為選用的預設專案。需能連線至該 DSS 實例。
安裝前請注意
API 金鑰可存取你的 DSS 實例,只應放在用戶端的環境設定中。多個工具會寫入或刪除資料:資料集、配方與情境的建立/更新/刪除,作業建置與中止,變數設定,資料夾上傳與刪除檔案。README 說明此伺服器已不再積極維護,並指向後續的 SDK。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Dataiku MCP,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

[!IMPORTANT]

Sunset — use clssck/dataiku-sdk instead

Dataiku MCP Server is no longer actively maintained. Development has moved to the Dataiku DSS SDK — a schema-first TypeScript SDK and dss CLI that is more actively maintained and covers far more of the DSS API:

  • Broader coverage — 30+ DSS resources vs this server's narrow tool set.
  • A scriptable dss CLI with a machine-readable command contract for agents.
  • One-command agent skill install for Claude, Codex, Cursor, Pi, and OMP.

Migrate here → https://github.com/clssck/dataiku-sdk


Dataiku MCP Server

MCP server for Dataiku DSS REST APIs, focused on flow analysis and reliable day-to-day operations (projects, datasets, recipes, jobs, scenarios, folders, variables, connections, and code environments).

[Install MCP Server]

Cursor one-click install includes placeholder environment values. Update DATAIKU_URL, DATAIKU_API_KEY, and optionally DATAIKU_PROJECT_KEY after adding the server.

What You Get

  • Deterministic normalized flow maps (project.map) with recipe subtypes and connectivity.
  • Summary-first outputs with explicit raw/detail toggles where needed.
  • Broad test coverage (unit + live integration + optional destructive integration suite).
  • Strong error taxonomy in responses: not_found, forbidden, validation, transient, unknown with retry hints.

Tool Coverage

  • project: list, get, metadata, flow, map
  • dataset: list, get, schema, preview, metadata, download, create, update, delete
  • recipe: list, get, create, update, delete, download
  • job: list, get, log, build, buildAndWait, wait, abort
  • scenario: list, run, status, get, create, update, delete
  • managed_folder: list, get, contents, download, upload, delete_file
  • variable: get, set
  • connection: infer
  • code_env: list, get

Prerequisites

  • Node.js 20+
  • npm
  • Dataiku DSS URL + API key

Quick Start

bash
npm cinpm run build

Run as a local CLI after build:

bash
node dist/index.js

Use directly from npm (after publish):

bash
npx -y dataiku-mcp

Local Build And Testing

Recommended local workflow from repo root:

bash
# install depsnpm ci
# static checksnpm run check
# unit testsnpm test
# build distributionnpm run build
# run MCP server locally (dev)npm start

Optional live DSS integration tests:

bash
# requires DATAIKU_URL, DATAIKU_API_KEY, DATAIKU_PROJECT_KEY in .envnpm run test:integration
# includes destructive actions (create/update/delete)DATAIKU_MCP_DESTRUCTIVE_TESTS=1 npm run test:integration

Repository Layout

  • src/: MCP server and tool implementations.
  • tests/: unit + integration test suites.
  • examples/: demos, fixtures, artifacts, and ad-hoc local scripts.
  • bin/: package executable entrypoint.
  • dist/: compiled output (generated).

Create a local env file:

bash
cp .env.example .env# then edit .env

Run directly in dev:

bash
npm start

Example scripts and sample outputs are kept under examples/ to avoid root-level clutter.

Environment Variables

  • DATAIKU_URL: DSS base URL
  • DATAIKU_API_KEY: DSS API key
  • DATAIKU_PROJECT_KEY (optional): default project key
  • DATAIKU_REQUEST_TIMEOUT_MS (optional): per-attempt request timeout in milliseconds (default: 30000)
  • DATAIKU_RETRY_MAX_ATTEMPTS (optional): max attempts for retry-enabled requests (GET only, default: 4, cap: 10)
  • DATAIKU_DEBUG_LATENCY (optional): set to 1/true to include per-tool timing diagnostics in structuredContent.debug.latency (off by default)

MCP Client Setup Guide

Use this server command in clients (npm package):

json
{  "command": "npx",  "args": ["-y", "dataiku-mcp"],  "env": {    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",    "DATAIKU_API_KEY": "your_api_key",    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"  }}

Windows note: if your MCP client launches commands without a shell, use npx.cmd:

json
{  "command": "npx.cmd",  "args": ["-y", "dataiku-mcp"],  "env": {    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",    "DATAIKU_API_KEY": "your_api_key",    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"  }}

You can also run TypeScript directly during development:

json
{  "command": "npx",  "args": ["tsx", "/absolute/path/to/Dataiku_MCP/src/index.ts"],  "env": {    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",    "DATAIKU_API_KEY": "your_api_key",    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"  }}

Claude Desktop

  1. Open Claude Desktop -> Settings -> Developer -> Edit Config.
  2. Add this under mcpServers in claude_desktop_config.json:
json
{  "mcpServers": {    "dataiku": {      "command": "npx",      "args": ["-y", "dataiku-mcp"],      "env": {        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",        "DATAIKU_API_KEY": "your_api_key",        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"      }    }  }}

Cursor

Cursor supports both project-scoped and global MCP config:

  • Project: .cursor/mcp.json
  • Global: ~/.cursor/mcp.json

Example:

json
{  "mcpServers": {    "dataiku": {      "command": "npx",      "args": ["-y", "dataiku-mcp"],      "env": {        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",        "DATAIKU_API_KEY": "your_api_key",        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"      }    }  }}

Cline (VS Code extension)

  1. Open Cline -> MCP Servers -> Configure MCP Servers.
  2. Add this server block in cline_mcp_settings.json:
json
{  "mcpServers": {    "dataiku": {      "command": "npx",      "args": ["-y", "dataiku-mcp"],      "env": {        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",        "DATAIKU_API_KEY": "your_api_key",        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"      }    }  }}

Codex / project-level MCP config

This repo already includes a project-scoped MCP file at .mcp.json. The checked-in .mcp.json uses node node_modules/tsx/dist/cli.mjs src/index.ts for cross-platform startup (including Windows); run npm ci first.

NPM Release Workflow

This repo includes a manual GitHub Actions release workflow:

  • Workflow file: .github/workflows/release.yml
  • Trigger: Actions -> Release NPM Package -> Run workflow

Inputs:

  • bump: patch | minor | major
  • version: optional exact version (overrides bump)
  • publish: whether to publish to npm

Required repository configuration:

  • GitHub variable: NPM_RELEASE_ENABLED=true
  • Optional variable: NPM_PUBLISH_ACCESS=public
  • Trusted publisher configured on npmjs.com for this package/repo/workflow

The workflow will:

  1. Install dependencies, run checks/tests, and build.
  2. Bump package version and create git tag.
  3. Push commit + tag to main.
  4. Publish to npm with GitHub OIDC trusted publishing (if publish=true).
  5. Create a GitHub Release with generated notes.

Trusted publishing setup (npm):

  1. Open https://www.npmjs.com/package/dataiku-mcp -> Settings -> Trusted Publisher.
  2. Choose GitHub Actions.
  3. Set:
    • Organization or user: clssck
    • Repository: Dataiku_MCP
    • Workflow filename: release.yml
  4. Save.

Official MCP Registry

This repo is configured for MCP Registry publishing:

  • Metadata file: server.json
  • Workflow: .github/workflows/publish-mcp-registry.yml
  • Required package field: mcpName in package.json

Server namespace:

  • io.github.clssck/dataiku-mcp

Publish paths:

  1. Manual: run Publish to MCP Registry in GitHub Actions.
  2. Automatic: run the npm release workflow with publish=true (it triggers MCP Registry publish).

Validation notes:

  • server.json.name must match package.json.mcpName.
  • server.json.packages[].identifier + version must reference a real npm publish.

Recommended Verification Prompt

After adding the server in a client, run:

  • project with { "action": "map", "projectKey": "YOUR_PROJECT_KEY" } (defaults to maxNodes=300, maxEdges=600; override as needed)

You should receive a flow summary in text and normalized nodes, edges, stats, roots, and leaves under structuredContent.map. When truncation limits are applied (default maxNodes=300, maxEdges=600), structuredContent.truncation reports before/after node+edge counts and whether truncation occurred.

Notes

  • project.map returns a compact text summary; full normalized graph is in structuredContent.map.
  • Arrays in normalized map output are deterministically sorted to reduce diff churn.
  • job.wait and job.buildAndWait include structuredContent.normalizedState with one of terminalSuccess | terminalFailure | timeout | nonTerminal while preserving raw DSS state.
  • With DATAIKU_DEBUG_LATENCY=1, responses include per-tool and per-API-call latency metrics under structuredContent.debug.latency.
  • List-style responses are token-bounded by default; use limit/offset (and action-specific caps like maxNodes, maxEdges, maxKeys, maxPackages) to page or expand results when needed.
  • dataset.get and job.get are summary-first by default; pass includeDefinition=true to include full DSS JSON in structuredContent.definition.

Sources

來源:README.md,提交 1d20e26

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v1.1.1最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分