data-marketplace-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@data-marketplace-mcp-server search for certified data products about customer churn in DACH region"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
|
Discovery | Metadaten & Ownership |
|
UX | Vorschau & Profiling |
|
Governance | Business Glossary |
|
Governance | Data Lineage |
|
Access | Zugriff anfordern („Warenkorb“) |
|
Access | Anfragen verwalten |
|
Access | Genehmigen / Ablehnen |
|
Publishing | Datenprodukt anbieten |
|
Trust | Zertifizierungs-Badge |
|
Feedback | Sterne-Bewertung |
|
Related MCP server: iceberg-mcp-server-hive
Demo-Szenario (Sarah & Thomas)
Suche:
search_data_products(query="Kundenhistorie Kündigungen", region="DACH", certified_only=true)Prüfung:
get_data_product("DP-SALES-CHURN-HIST"),preview_data_product(...),get_product_lineage(...)Zugriff:
request_data_access(...)mit Nutzungszweck und ZielumgebungGenehmigung: Thomas ruft
approve_access_request(...)auf → automatisches ProvisioningFeedback:
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
Build & push image:
docker build -t data-marketplace-mcp:0.1.0 .In Cloudera AI Workbench eine neue Application anlegen:
Runtime: Docker
Port:
8080Env: siehe
cai-workbench/app.yaml
Persistent volume auf
/datamounten (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-marketplaceWorkbench-Agents verbinden sich per MCP Streamable HTTP auf Port 8080.
Konfiguration
Variable | Default | Beschreibung |
|
|
|
|
| Bind-Adresse (HTTP) |
|
| Port (HTTP) |
|
| Persistenz für Produkte & Anfragen |
| — | Optional: Atlas-Katalog anreichern |
| — | Knox/Atlas Auth |
| — | Optional: Ranger/Entra-ID Automation |
Atlas-Integration (CDP)
Wenn ATLAS_* gesetzt ist:
search_data_productsliefert zusätzlich Atlas-Treffer (hive_table,iceberg_table)get_product_lineagenutzt Atlas Lineage APIsearch_glossarydurchsucht 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-entraDer 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 toolsapprove_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
Scored across 16 tools
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.
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.
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.
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
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
AI-Ready Data Platform that fills the missing layer between data management and AI execution.
AI-powered data integration platform. Onboard users and run DPF data workflows.
Company and industrial data for AI assistants: datasets, SQL, dashboards, alarms, with approvals.
Related MCP Servers
- AlicenseAqualityFmaintenanceEnables 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.446MIT
- AlicenseAqualityCmaintenanceProvides read-only SQL access to Apache Iceberg tables via HiveServer2, enabling querying, schema discovery, and database listing on Cloudera Data Platform.31Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables 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
- FlicenseNot gradedqualityDmaintenanceEnables composable search and filtering over an enterprise data catalog, with tools for lineage, sample data, profiling, history, quality rules, and AI-driven classification.-