Overture MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Interactive React Flow canvas — pan, zoom, node-level controls
Dynamic inputs (text, number, boolean, secret, file attachment)
Branch comparison with pros/cons before choosing
One-line install across Claude Code, Cursor, Cline, Copilot

Démo en direct

Aperçu en pratique

overture.replay ▶ prêt

0/0

Installer

Choisissez votre client

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

{
  "mcpServers": {
    "overture": {
      "command": "npx",
      "args": [
        "-y",
        "Overture"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "overture": {
      "command": "npx",
      "args": [
        "-y",
        "Overture"
      ],
      "_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": {
    "overture": {
      "command": "npx",
      "args": [
        "-y",
        "Overture"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "overture": {
      "command": "npx",
      "args": [
        "-y",
        "Overture"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "overture",
      "command": "npx",
      "args": [
        "-y",
        "Overture"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "overture": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "Overture"
        ]
      }
    }
  }
}

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

claude mcp add overture -- npx -y Overture

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

Cas d'usage

Usages concrets : Overture

Review your agent's plan in a flowchart before it writes code

👤 Anyone running coding agents on real repos ⏱ ~15 min beginner

Quand l'utiliser : You've been burned by an agent confidently writing 800 lines of wrong code — you want a gate.

Prérequis

Claude Code or equivalent agent — claude.ai/code

Déroulement

Install

Run claude mcp add overture-mcp -- npx overture-mcp to wire it into Claude Code.✓ Copié

→ Overture web UI reachable at shown URL
Ask for a feature; plan opens in canvas

Implement an auth middleware. Before coding, use overture to produce a plan graph.✓ Copié

→ Nodes for each step appear in the Overture UI
Approve or redirect nodes

Node 3 looks wrong — reject it with a comment 'use existing middleware at ./lib/auth.ts instead'✓ Copié

→ Plan regenerates; agent only codes after you press approve

Résultat : Agent writes code you actually asked for — you caught the wrong assumption at step 3, not commit 3.

Pièges

Canvas becomes noisy on huge features — Break feature into sub-plans; Overture supports multi-project tabs

Combiner avec : claude-code

Compare two implementation approaches side by side

👤 Engineers choosing between designs ⏱ ~20 min intermediate

Quand l'utiliser : You're torn between two approaches (Redis cache vs in-memory) and want the agent to plan both.

Déroulement

Ask for two branches

Plan this caching feature in two branches: (A) Redis, (B) in-memory LRU. Show pros/cons for each.✓ Copié

→ Overture renders two branches with comparison
Pick and execute

Approve branch B. Execute only that path.✓ Copié

→ Only the chosen branch runs

Résultat : Informed decision between alternatives without committing code to both.

Inject secrets into a plan node without committing them

👤 Anyone scripting deploy plans ⏱ ~10 min intermediate

Quand l'utiliser : A step needs an API key; you want to provide it at run-time, not in the prompt history.

Déroulement

Mark the node as needing a secret

The deploy node needs DEPLOY_TOKEN as a secret input. Pause until provided.✓ Copié

→ Overture shows a secret field awaiting input
Paste into the UI; node unlocks

(in Overture UI) paste token and click resume✓ Copié

→ Plan continues; secret not in chat history

Résultat : Agents run privileged steps without secrets leaking into transcripts.

Combinaisons

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

overture + claude-code

Use Overture as the approval layer for every Claude Code task

From now on, for any task estimated >30 min, use overture to plan before coding.✓ Copié

overture + vibe-check

Plan → sanity check → execute

After Overture produces a plan, run vibe_check on it before I approve.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
plan_create	goal: str, context?: str	Start of any multi-step coding task	LLM tokens for planning
plan_update	plan_id, node_changes	React to user approve/reject	0
plan_execute	plan_id, from_node?	After user approval	tool calls + tokens
plan_branch	plan_id, from_node, alt_goal	Compare alternatives	LLM tokens

Coût et limites

Coût d'exécution

Quota d'API: None — local app
Tokens par appel: Planning adds ~1-3k tokens up front; saves more in avoided wrong code
Monétaire: Free, open source
Astuce: Use plans only for non-trivial features; trivial edits don't need a graph

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Secrets entered in the UI, stored in local browser storage per plan

Sortie de données : None by default — runs on localhost

Dépannage

Erreurs courantes et correctifs

Canvas URL returns ERR_CONNECTION_REFUSED

Overture UI port (default 3939) not bound; check MCP server logs or set OVERTURE_PORT

Vérifier : curl http://localhost:3939

Plan generation hangs

Your agent is waiting on LLM; check the agent's own logs for rate limit / token exhaustion

Node rejections not taking effect

Some agents cache plans — explicitly say 'regenerate the plan from node X with my feedback'

Alternatives

Overture vs autres

Alternative	Quand l'utiliser	Compromis
sequentialthinking-tools	You want a text plan, not a canvas	No visual comparison of branches
shrimp-task-manager	You want persistent tasks, not interactive approval	Different loop — more async, less gated

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills