Unstructured UNS MCP — Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

60+ source connectors (S3, Drive, OneDrive, SharePoint, GCS)
Document partitioning into elements (Title, Table, NarrativeText, ListItem)
Built-in chunkers (by_title, basic)
Embeddings via OpenAI, Voyage, or local models
Targets: vector DBs (Pinecone, Weaviate, Qdrant) or warehouses

Live-Demo

In der Praxis

unstructured-uns-mcp.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "unstructured-uns-mcp",
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "unstructured-uns-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "uns-mcp"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add unstructured-uns-mcp -- uvx uns-mcp

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: Unstructured UNS MCP

Stand up a RAG pipeline from a SharePoint folder to Pinecone

👤 Data engineers / RAG builders ⏱ ~15 min intermediate

Wann einsetzen: You have a corporate doc dump and want a Claude-queryable index.

Voraussetzungen

Server/skill installed and authenticated — See repo README

Ablauf

Define the pipeline

Create an Unstructured pipeline: source SharePoint folder X, partition by_title with 1024 token max, embed with text-embedding-3-small, target Pinecone index 'corp-docs'.✓ Kopiert

→ Pipeline id
Run and monitor

Run it and tell me when it's done. Report any failed documents.✓ Kopiert

→ Status updates + final summary

Ergebnis: Production-grade ingest with proper chunking — not naive PDF text dumps.

Fallstricke

Default chunkers can split tables across chunks. For dense tabular docs, use 'by_title' with combine_text_under_n_chars. — Default chunkers can split tables across chunks. For dense tabular docs, use 'by_title' with combine_text_under_n_chars.

Kombinieren mit: filesystem · qdrant-mcp-server

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

unstructured-uns-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ Kopiert

unstructured-uns-mcp + qdrant-mcp-server

Pair with qdrant-mcp-server for complementary capabilities

Use this server together with qdrant-mcp-server to complete a multi-step task.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
create_pipeline	source, dest, partition_args, chunk_args	Define a new ingest job	1 API call
run_pipeline	pipeline_id	Execute the pipeline	Per Unstructured plan
list_workflows	(none)	See all configured workflows	1 API call

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: See provider docs for rate limits
Tokens pro Aufruf: Varies by tool
Kosten in €: See repo README for pricing details
Tipp: Cache tool results and avoid repeated identical calls.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Use environment variables; never commit secrets

Datenabfluss: Tool calls go to the provider's API as documented

Fehlerbehebung

Häufige Fehler und Lösungen

401 Unauthorized

Get an API key at unstructured.io → Settings → API keys; set UNSTRUCTURED_API_KEY and UNSTRUCTURED_API_URL.

Prüfen: list_workflows returns at least one

source connector auth failure

Connector creds (e.g. SharePoint app token) are configured per-source. Recreate the source via Unstructured UI to refresh.

Prüfen: Run a 1-file test pipeline first

Alternativen

Unstructured UNS MCP vs. andere

Alternative	Wann stattdessen	Kompromiss
LlamaIndex / llamacloud	You want a managed RAG-as-a-service product	Higher-level but less control over chunking

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen