🔥 The Problem
Every AI coding agent today — Cursor, Claude Code, Cline, Copilot — works the same way:
接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Every AI coding agent today — Cursor, Claude Code, Cline, Copilot — works the same way:
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.
Some agents show plans as text in chat. But text fails to show:
Overture intercepts your AI agent's planning phase and renders it as an interactive visual flowchart — before any code is written.
Overture is an MCP server that works with any MCP-compatible AI coding agent. One command to install.
claude mcp add overture-mcp -- npx overture-mcp
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"]
}
}
}
Open VS Code settings → search "Cline MCP" → add:
{
"mcpServers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"]
}
}
}
Create .vscode/mcp.json in your project root:
{
"servers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"]
}
}
}
Note: GitHub Copilot MCP requires VS Code 1.99+ and uses
serversinstead ofmcpServers.
Add to your Sixth AI MCP settings file:
{
"mcpServers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"],
"disabled": false
}
}
}
npm install -g overture-mcp
Give your agent any task. Overture automatically opens at http://localhost:3031 with your plan ready for approval.
The Flow:
Click any node to reveal its full details:
Nodes can request input from you before execution:
Each field includes:
Attach context files to specific nodes:
Add custom LLM instructions to any node:
"Pay special attention to error handling here" "Use the existing auth pattern from src/auth.ts" "Make sure to add tests for edge cases"
Instructions are sent to the agent right before that node executes.
When the agent proposes multiple approaches:
Before you can approve, Overture shows what's needed:
The Approve button stays disabled until all requirements are met.
The approval button is smart:
After each node executes, see rich structured output:
Each category is expandable — drill in without visual overload.
Click any completed node to see full output:
Browse and attach MCP servers directly from the Overture UI.
When you attach an MCP server to a node, the agent gains access to those tools only for that step.
Work on multiple projects simultaneously:
Single project? Tab bar hides automatically for a cleaner UI.
Never lose your work:
When resuming, you get complete context:
Modify plans even during execution:
When a plan changes, see exactly what's different:
Overture exposes 11 MCP tools for agents to interact with:
19 server-to-client message types:
connected • plan_started • node_added • edge_added • plan_ready • plan_approved • node_status_updated • plan_completed • plan_failed • plan_paused • plan_resumed • nodes_inserted • node_removed • project_registered • projects_list • history_entries • plan_loaded • resume_plan_info • plan_updated
16 client-to-server message types:
approve_plan • cancel_plan • rerun_request • pause_execution • resume_execution • insert_nodes • remove_node • register_project • subscribe_project • unsubscribe_project • get_history • load_plan • get_resume_info • save_plan • request_plan_update • create_new_plan
When the WebSocket port is already in use, Overture automatically operates as a relay client, forwarding messages through the existing server. Multiple agent instances can share a single UI.
claude mcp add overture-mcp -e OVERTURE_HTTP_PORT=4000 -e OVERTURE_AUTO_OPEN=false -- npx overture-mcp
{
"mcpServers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"],
"env": {
"OVERTURE_HTTP_PORT": "4000",
"OVERTURE_WS_PORT": "4001",
"OVERTURE_AUTO_OPEN": "false"
}
}
}
}
{
"servers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"],
"env": {
"OVERTURE_HTTP_PORT": "4000",
"OVERTURE_WS_PORT": "4001",
"OVERTURE_AUTO_OPEN": "false"
}
}
}
}
Each agent has custom-tailored prompts for optimal plan generation.
# Clone the repo
git clone https://github.com/SixHq/Overture.git
cd Overture
# Install dependencies
npm install
# Build all packages
npm run build
# Start MCP server (in one terminal)
cd packages/mcp-server && npm start
# Start UI dev server (in another terminal)
cd packages/ui && npm run dev
Overture is open source and we welcome contributions!
All contributions are appreciated, no matter how small.
MIT License - see LICENSE for details.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowcha
總覽
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Overture 透過 stdio 在本機執行。
上次檢查時間:2026-11-05。 Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server that visually maps out the execution plan of any AI coding agent as an interactive flowchart/graph before the agent begins writing code.