Unstructured UNS MCP — Instalar & Demo en vivo

Por qué usarlo

Características clave

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

Demo en vivo

Cómo se ve en la práctica

unstructured-uns-mcp.replay ▶ listo

0/0

Instalar

Elige tu cliente

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

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

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: Unstructured UNS MCP

Stand up a RAG pipeline from a SharePoint folder to Pinecone

👤 Data engineers / RAG builders ⏱ ~15 min intermediate

Cuándo usarlo: You have a corporate doc dump and want a Claude-queryable index.

Requisitos previos

Server/skill installed and authenticated — See repo README

Flujo

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'.✓ Copiado

→ Pipeline id
Run and monitor

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

→ Status updates + final summary

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

Errores comunes

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.

Combinar con: filesystem · qdrant-mcp-server

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

unstructured-uns-mcp + filesystem

Pair with filesystem for complementary capabilities

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

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.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
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

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: See provider docs for rate limits
Tokens por llamada: Varies by tool
Monetario: See repo README for pricing details
Consejo: Cache tool results and avoid repeated identical calls.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: Use environment variables; never commit secrets

Salida de datos: Tool calls go to the provider's API as documented

Resolución de problemas

Errores comunes y soluciones

401 Unauthorized

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

Verificar: 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.

Verificar: Run a 1-file test pipeline first

Alternativas

Unstructured UNS MCP vs otros

Alternativa	Cuándo usarla	Contrapartida
LlamaIndex / llamacloud	You want a managed RAG-as-a-service product	Higher-level but less control over chunking

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills