cocoindex-claude MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Drop-in knowledge of CocoIndex flow definitions, sources, and sinks
Guidance on writing custom transformation functions correctly
Claude picks the right CLI vs programmatic API based on task
Understands incremental processing semantics so it doesn't suggest full rebuilds
Official — authored by the CocoIndex team

Démo en direct

Aperçu en pratique

cocoindex-claude-skill.replay ▶ prêt

0/0

Installer

Choisissez votre client

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

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "cocoindex-claude-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "cocoindex-claude-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/cocoindex-io/cocoindex-claude",
          "~/.claude/skills/cocoindex-claude"
        ]
      }
    }
  }
}

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

claude mcp add cocoindex-claude-skill -- git clone https://github.com/cocoindex-io/cocoindex-claude ~/.claude/skills/cocoindex-claude

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

Cas d'usage

Usages concrets : cocoindex-claude

Build your first CocoIndex pipeline from a local folder into a vector DB

👤 Developers evaluating CocoIndex for a RAG use case ⏱ ~30 min intermediate

Quand l'utiliser : You've read the CocoIndex homepage and want Claude to scaffold a working flow instead of copy-pasting tutorials.

Prérequis

Skill cloned to ~/.claude/skills/cocoindex-claude — git clone https://github.com/cocoindex-io/cocoindex-claude ~/.claude/skills/cocoindex-claude
cocoindex Python package installed — pip install cocoindex

Déroulement

Describe the pipeline

Use the cocoindex skill — scaffold a flow that watches ./docs, chunks markdown, embeds with OpenAI, writes to Qdrant.✓ Copié

→ Claude generates a flow.py with @cocoindex.flow_def and the right source/transform/export calls
Run and verify

Now show me the exact CLI commands to build, run, and incrementally update this flow.✓ Copié

→ cocoindex setup / update / eval commands in the correct order

Résultat : A working flow.py plus the commands to run it — no more guessing at the CocoIndex decorator surface.

Pièges

Claude invents APIs that don't exist in CocoIndex — Explicitly prompt 'use only APIs documented in the cocoindex skill' — hallucination drops when the skill is in scope

Combiner avec : filesystem

Write a custom CocoIndex transform function

👤 Engineers extending an existing CocoIndex flow ⏱ ~25 min intermediate

Quand l'utiliser : Built-in transforms don't cover your parsing / enrichment step.

Déroulement

Describe the transform

With the cocoindex skill — write a @cocoindex.op.function that takes a PDF path, extracts tables, returns structured rows.✓ Copié

→ Idiomatic function signature with correct typed inputs/outputs
Wire it into the flow

Now plug this into my existing flow at the chunking stage.✓ Copié

→ Diff against current flow.py with the new op in place

Résultat : A custom transform that obeys CocoIndex's incremental semantics.

Pièges

Function returns non-deterministic output, breaking incremental processing — Skill reminds Claude that transforms must be pure — if you hit this, re-read the incremental section

Combinaisons

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

cocoindex-claude-skill + filesystem

Let Claude actually write the flow.py file to disk, not just print it in chat

Scaffold the CocoIndex flow and save it to ./pipelines/docs_to_qdrant.py.✓ Copié

cocoindex-claude-skill + postgres

Pipe CocoIndex output into a Postgres vector store and query it from the same session

Build the flow targeting pgvector, then run a retrieval query against it.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
scaffold_flow	source type + sink type + transform steps	Starting a new pipeline
write_custom_op	function intent + input/output types	Built-in transforms aren't enough
cli_guidance	task (setup / update / eval / drop)	You're unsure whether to rebuild or incrementally update

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: Modest — skill loads reference material only when relevant
Monétaire: Free — skills are local files
Astuce: CocoIndex itself is free; costs come from your embedding model and vector DB, not this skill.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : No credentials — pure prompts

Sortie de données : None from the skill itself. Your pipeline calls whichever embedding / DB services you configure.

Dépannage

Erreurs courantes et correctifs

Skill not invoked when you ask about CocoIndex

Say 'use the cocoindex skill' explicitly, or check it's installed at ~/.claude/skills/cocoindex-claude.

Vérifier : ls ~/.claude/skills/cocoindex-claude/SKILL.md

SKILL.md frontmatter wrong

Open the file and verify name / description are populated. Re-clone if partial.

Vérifier : head ~/.claude/skills/cocoindex-claude/SKILL.md

Wrong trigger keywords — Claude writes generic Python instead of CocoIndex

Mention CocoIndex explicitly, or say 'scaffold a cocoindex flow_def'.

Alternatives

cocoindex-claude vs autres

Alternative	Quand l'utiliser	Compromis
LlamaIndex skills	You want LlamaIndex's retrieval abstractions instead of CocoIndex's transform-centric model	Different mental model — LlamaIndex is retrieval-first, CocoIndex is pipeline-first
Hand-written Python	You need one-off processing and don't want incremental state	No incremental rebuilds, no framework conventions

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills