Log inSubmit server
Overture MCP logo

Overture MCP

Visualizes coding-agent plans for review, enrichment, approval, and monitored execution through an interactive flowchart.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Overture MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "overture-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "overture-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y overture-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

overture-mcp MCP server adds a visual planning and approval workflow to MCP-compatible coding agents. It turns an agent’s generated plan into an interactive graph where you can inspect dependencies, attach files or inputs, choose branches, and approve execution before code is written. The browser interface opens at localhost:3031 and shows node status as work progresses. Reach for it when you want more control and visibility than a text-only coding-agent plan.

Use cases

  • Review an agent’s implementation plan before code changes begin
  • Attach files and API keys to individual execution steps
  • Compare alternative approaches through plan branches
  • Monitor node-by-node coding-agent progress
  • Pause, rerun, or modify work during execution

Key features

  • Interactive visual plan canvas
  • Streaming node and execution status
  • Branch selection and plan editing
  • Per-node files, secrets, and dynamic inputs
  • Complexity, risk, and expected-output details
  • Pause, resume, and node rerun controls

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

8/8 checks healthy over the last 15d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12h ago via OSV.dev · overture-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars643Stargazers on the source repository.
Last commit8mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.

How Overture MCP works

What overture-mcp does

overture-mcp places a review step between an AI coding agent’s planning and implementation phases. The agent produces a structured plan, and Overture presents it as an interactive flowchart before execution begins. You can inspect individual steps, review expected outputs and risks, compare branch options, and approve the plan when it is ready.

The workflow is intended for tasks where an incorrect interpretation could lead to substantial rework. It supports coding agents including Claude Code, Cursor, Cline, GitHub Copilot, and Windsurf, with installation through each client’s MCP configuration.

How it works

After you give the coding agent a task, Overture receives the generated plan and renders its nodes as they arrive. The graph can be panned, zoomed, and navigated by selecting nodes. Automatic layout positions the plan, while visual states distinguish pending, active, completed, and failed work. Complexity indicators and a next-node marker provide additional status information.

Before execution, you can enrich the plan by attaching files, entering values, supplying secrets through masked fields, or selecting among alternative branches. Approval starts execution; the interface then shows progress in real time. During the run, you can pause and resume the workflow, rerun nodes, or modify the plan. Nodes can also be inserted between existing steps through the graph’s edges.

Setup and configuration

The server can be run directly with npx and configured as a local stdio MCP server. For Claude Code, use:

Terminal
claude mcp add overture-mcp -- npx overture-mcp

Cursor, Cline, GitHub Copilot, and Sixth AI use JSON MCP configuration with npx as the command and overture-mcp as its argument. A global installation is also available:

Terminal
npm install -g overture-mcp

When the server is working, Overture opens its interface at http://localhost:3031 after an agent receives a task.

Tools and capabilities

  • Render agent plans as interactive flowcharts with pan, zoom, drag, and click-through navigation.
  • Stream plan nodes into the canvas while the agent generates them.
  • Display task complexity, dependencies, branches, risks, expected outputs, and execution state.
  • Collect string, number, boolean, select, secret, and file inputs at individual nodes.
  • Attach files, API keys, and instructions to plan steps.
  • Compare the pros and cons of alternative approaches.
  • Approve, pause, resume, rerun, or modify execution from the visual workflow.
  • Browse and attach MCP tools per node through the MCP marketplace feature.

Limitations and notes

Overture’s workflow depends on the coding agent producing a plan that the server can render. Execution does not begin until the plan is approved in the interface. The local web interface uses port 3031, so another service occupying that port may prevent it from opening as expected. GitHub Copilot requires the VS Code-specific configuration format rather than mcpServers.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Overture MCP

overture-mcp is an MCP server that connects AI coding agents such as Claude Code, Cursor, Cline, GitHub Copilot, and Windsurf to a visual plan approval interface. Its main capabilities are rendering agent plans as interactive flowcharts, collecting per-step context, and monitoring approved execution.

Install it by adding `npx overture-mcp` to your MCP client configuration, or run `claude mcp add overture-mcp -- npx overture-mcp` for Claude Code. You can also install the npm package globally with `npm install -g overture-mcp`.

Yes, overture-mcp works with Cursor through its MCP configuration. Add an `overture` server using `npx` as the command and `overture-mcp` as the argument in `~/.cursor/mcp.json`.

Overture opens a local interface at `http://localhost:3031` and displays the agent’s plan as a graph. Review or enrich the nodes, then select the approval control to begin execution.

Yes, GitHub Copilot is supported through a `.vscode/mcp.json` configuration. Use the `servers` property instead of `mcpServers`, and use VS Code 1.99 or newer for Copilot MCP.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOverture MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/overture-mcp?style=directory)](https://allmcps.com/mcp/overture-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/overture-mcp"><img src="https://allmcps.com/api/badge/overture-mcp?style=directory" alt="Overture MCP on AllMCPs" /></a>