/ Annuaire / Playground / Unstructured UNS MCP
● Officiel unstructured-io ⚡ Instantané

Unstructured UNS MCP

par unstructured-io · unstructured-io/uns-mcp

Parse, chunk, and embed any document with Unstructured's pipeline.

Unstructured's library extracts clean text and structure from messy documents (PDFs, scans, PPTX, emails). This MCP wraps the Unstructured Serverless pipeline so Claude can ingest a folder of raw files and turn them into a queryable RAG corpus.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

unstructured-uns-mcp.replay ▶ prêt
0/0

Installer

Choisissez votre 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"
      ]
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "unstructured-uns-mcp": {
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "unstructured-uns-mcp",
      "command": "uvx",
      "args": [
        "uns-mcp"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json
{
  "context_servers": {
    "unstructured-uns-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "uns-mcp"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : Unstructured UNS MCP

Stand up a RAG pipeline from a SharePoint folder to Pinecone

👤 Data engineers / RAG builders ⏱ ~15 min intermediate

Quand l'utiliser : You have a corporate doc dump and want a Claude-queryable index.

Prérequis
  • Server/skill installed and authenticated — See repo README
Déroulement
  1. 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'.✓ Copié
    → Pipeline id
  2. Run and monitor
    Run it and tell me when it's done. Report any failed documents.✓ Copié
    → Status updates + final summary

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

Pièges
  • 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.
Combiner avec : filesystem · qdrant-mcp-server

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

unstructured-uns-mcp + filesystem

Pair with filesystem for complementary capabilities

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

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
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

Coût et limites

Coût d'exécution

Quota d'API
See provider docs for rate limits
Tokens par appel
Varies by tool
Monétaire
See repo README for pricing details
Astuce
Cache tool results and avoid repeated identical calls.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Use environment variables; never commit secrets
Sortie de données : Tool calls go to the provider's API as documented

Dépannage

Erreurs courantes et correctifs

401 Unauthorized

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

Vérifier : 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.

Vérifier : Run a 1-file test pipeline first

Alternatives

Unstructured UNS MCP vs autres

AlternativeQuand l'utiliserCompromis
LlamaIndex / llamacloudYou want a managed RAG-as-a-service productHigher-level but less control over chunking

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills