Skip to main content
Glama
data-marketplace-mcp-server

data-marketplace-mcp-server

by frothkoetter

Internal Data Marketplace MCP Server

MCP-Agent für einen internen Data Marketplace (Data Mesh Store / Internal Data Portal) — optimiert für Cloudera AI Workbench.

Der Fokus liegt auf Kollaboration, Governance und Systemintegration: Datensilos aufbrechen, damit Teams Daten self-service finden, prüfen und freigeben lassen können — ohne monatelange IT-Tickets.

Basisfunktionen

Bereich

Funktion

MCP-Tool

Discovery

Unternehmensweiter Datenkatalog

search_data_products

Discovery

Metadaten & Ownership

get_data_product

UX

Vorschau & Profiling

preview_data_product

Governance

Business Glossary

search_glossary

Governance

Data Lineage

get_product_lineage

Access

Zugriff anfordern („Warenkorb“)

request_data_access

Access

Anfragen verwalten

list_access_requests

Access

Genehmigen / Ablehnen

approve_access_request, reject_access_request

Publishing

Datenprodukt anbieten

publish_data_product

Trust

Zertifizierungs-Badge

certify_data_product

Feedback

Sterne-Bewertung

submit_product_feedback

Related MCP server: iceberg-mcp-server-hive

Demo-Szenario (Sarah & Thomas)

  1. Suche: search_data_products(query="Kundenhistorie Kündigungen", region="DACH", certified_only=true)

  2. Prüfung: get_data_product("DP-SALES-CHURN-HIST"), preview_data_product(...), get_product_lineage(...)

  3. Zugriff: request_data_access(...) mit Nutzungszweck und Zielumgebung

  4. Genehmigung: Thomas ruft approve_access_request(...) auf → automatisches Provisioning

  5. Feedback: submit_product_feedback(...) nach Nutzung

Lokale Entwicklung

cd data-marketplace-mcp-server
uv sync
uv run python -m pytest tests/ -q
uv run run-marketplace   # stdio MCP (Cursor / Claude Desktop)

Cloudera AI Workbench Deployment

Option A: Docker Application

  1. Build & push image:

    docker build -t data-marketplace-mcp:0.1.0 .
  2. In Cloudera AI Workbench eine neue Application anlegen:

    • Runtime: Docker

    • Port: 8080

    • Env: siehe cai-workbench/app.yaml

  3. Persistent volume auf /data mounten (MARKETPLACE_DATA_DIR).

Option B: HTTP MCP für Workbench Agents

export MCP_TRANSPORT=http
export MCP_HOST=0.0.0.0
export MCP_PORT=8080
export MARKETPLACE_DATA_DIR=/data
run-marketplace

Workbench-Agents verbinden sich per MCP Streamable HTTP auf Port 8080.

Konfiguration

Variable

Default

Beschreibung

MCP_TRANSPORT

stdio

stdio oder http für Workbench

MCP_HOST

0.0.0.0

Bind-Adresse (HTTP)

MCP_PORT

8080

Port (HTTP)

MARKETPLACE_DATA_DIR

./data

Persistenz für Produkte & Anfragen

ATLAS_GATEWAY_URL

—

Optional: Atlas-Katalog anreichern

ATLAS_USER / ATLAS_PASS

—

Knox/Atlas Auth

MARKETPLACE_PROVISIONING_WEBHOOK

—

Optional: Ranger/Entra-ID Automation

Atlas-Integration (CDP)

Wenn ATLAS_* gesetzt ist:

  • search_data_products liefert zusätzlich Atlas-Treffer (hive_table, iceberg_table)

  • get_product_lineage nutzt Atlas Lineage API

  • search_glossary durchsucht Atlas Business Glossary

Provisioning (Erweiterung)

Standardmäßig simuliert approve_access_request das Provisioning (Gruppenzuweisung, Zugriff freischalten). Für echte Automation einen Webhook setzen:

export MARKETPLACE_PROVISIONING_WEBHOOK=https://your-provisioner/ranger-or-entra

Der Webhook erhält JSON mit request und product und kann Ranger Policies oder Entra-ID-Gruppen steuern.

MCP in Cursor konfigurieren

{
  "mcpServers": {
    "data-marketplace": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/data-marketplace-mcp-server", "run-marketplace"],
      "env": {
        "ATLAS_GATEWAY_URL": "https://<host>/<topology>/cdp-proxy-api/atlas/api/atlas/",
        "ATLAS_USER": "<user>",
        "ATLAS_PASS": "<pass>"
      }
    }
  }
}

Lizenz

Apache-2.0

Available Tools

16 tools
approve_access_requestC

Zugriffsanfrage genehmigen und automatisches Provisioning anstoßen.

Inputs: approver (required), request_id (required), comment. Returns: result

certify_data_productB

Qualitätssiegel setzen (verified, certified, deprecated).

Inputs: product_id (required), certification. Returns: result

ensure_data_marketplace_typedefB

Register or upgrade the data_marketplace_product entity typedef in Atlas (serviceType: data_mesh). WRITE OPERATION

Inputs: no named parameters. Returns: result

get_data_productB

Metadaten, Ownership, Zertifizierung und Governance eines Datenprodukts laden.

Inputs: product_id (required). Returns: result

get_product_lineageC

Data Lineage (Daten-Stammbaum) für ein Produkt — inkl. Atlas wenn konfiguriert.

Inputs: product_id (required), depth. Returns: result

list_access_requestsC

Subscriber/Zugriffsanfragen auflisten.

Im Data-Contract-Modus werden consumer-Einträge aus dem governing data_contract gelesen.

Inputs: status, requester, product_id, owner_contact. Returns: result

list_product_subscribersC

Subscriber eines Datenprodukts aus dem governing Data Contract lesen.

Inputs: product_id (required). Returns: result

marketplace_overviewB

Übersicht über den internen Data Marketplace und seine Basisfunktionen.

Inputs: no named parameters. Returns: result

preview_data_productB

Anonymisierte Datenvorschau und Spalten-Profiling für ein Datenprodukt.

Inputs: product_id (required), limit. Returns: result

publish_data_productC

Neues Datenprodukt registrieren (Data Publishing Wizard für Data Owner).

Inputs: name (required), domain (required), region (required), owner_team (required), +12 more. Returns: result

reject_access_requestC

Zugriffsanfrage ablehnen.

Inputs: reason (required), approver (required), request_id (required). Returns: result

request_data_accessA

Zugriff anfordern / abonnieren — registriert Subscriber im Data Contract consumer-Attribut (Atlas).

Wenn MARKETPLACE_USE_DATA_CONTRACT_SUBSCRIBERS=true (Default), wird kein lokaler Subscriber-Datensatz angelegt; der Data Contract ist Single Source of Truth.

Args: product_id: z. B. DP-MART-CREDIT-QUALITY-MATRIX requester: E-Mail oder User-ID der antragstellenden Person purpose: Nutzungszweck (DSGVO/Revision) project: Projektname duration_months: Zugriffsdauer in Monaten target_environment: Zielumgebung (z. B. marketing-snowflake)

Inputs: project (required), purpose (required), requester (required), product_id (required), +2 more. Returns: result

search_data_productsA

Datenkatalog durchsuchen — wie Produktsuche im internen Marktplatz.

Args: query: Freitext (z. B. 'Kundenhistorie Kündigungen'). region: Region filtern (z. B. 'DACH'). certified_only: Nur zertifizierte/verifizierte Produkte. domain: Fachdomäne (z. B. 'sales', 'marketing'). limit: Maximale Trefferzahl.

Inputs: limit, query, domain, region, +1 more. Returns: result

search_glossaryB

Business Glossary durchsuchen — übersetzt technische Begriffe für Business-Nutzer.

Inputs: query (required), limit. Returns: result

submit_product_feedbackD

Sterne-Feedback zur Datenqualität abgeben (1–5).

Inputs: user (required), rating (required), product_id (required), comment. Returns: result

sync_data_product_to_atlasA

Sync marketplace product(s) to Atlas as data_marketplace_product entities. WRITE OPERATION

Args: product_id: Optional product ID. If omitted, syncs all local marketplace products. link_dataset: Link each product to its underlying Atlas dataset when atlas_qualified_name is set.

Inputs: product_id, link_dataset. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 16 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: searching, viewing, requesting access, publishing, and sync operations cover separate concerns. However, list_access_requests and list_product_subscribers both deal with subscribers/access and could cause some confusion about which to use for a given scenario.

    Naming Consistency4/5

    The naming follows a strong verb_noun pattern (search_data_products, get_data_product, preview_data_product, publish_data_product, certify_data_product). Minor deviations exist: ensure_data_marketplace_typedef and get_product_lineage break the strict pattern but are still readable and descriptive.

    Tool Count4/5

    At 16 tools, this sits slightly above the ideal sweet spot but is reasonable for a marketplace with search, product lifecycle, access management, and Atlas sync capabilities. Most tools earn their place, though the two ‘WRITE OPERATION’ Atlas sync tools are somewhat operational rather than user-facing.

    Completeness4/5

    The surface covers search, view, preview, lineage, glossary, access lifecycle (request/list/approve/reject), publishing, certification, and feedback. Minor gaps include no explicit update/delete for data products (only publish/create) and subscription management beyond listing, but the core marketplace workflow is well covered.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      F
      maintenance
      Enables AI agents to discover, request access to, and query data products in Data Mesh Manager, enforcing governance policies while retrieving business data from platforms like Snowflake and Databricks.
      4
      46
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Provides read-only SQL access to Apache Iceberg tables via HiveServer2, enabling querying, schema discovery, and database listing on Cloudera Data Platform.
      3
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables enterprise AI agents to query governed data lineage, PII-aware schema documentation, and semantic metadata from SQL logs via MCP, with role-based access and vector search.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables composable search and filtering over an enterprise data catalog, with tools for lineage, sample data, profiling, history, quality rules, and AI-driven classification.
      -