Overture
Visual plan approval for AI coding agents. See your agent's plan as an interactive graph, attach context, choose approaches, then approve before any code is written.
Ads
Overview
https://github.com/user-attachments/assets/eeb9c4cb-c80d-42da-bf63-c0c4ecb1e5d6 Every AI coding agent today — Cursor, Claude Code, Cline, Copilot — works the same way: 1. You type a prompt 2. Agent immediately starts writing code 3. You have zero visibility into what it's doing 4. You realize it misunderstood your request 5. Hundreds of lines of code need to be discarded 6. You've wasted tokens, time, and patience Some agents show plans as text in chat. But text fails to show: - Dependencies — which tasks depend on what? - Branch points — what alternative approaches exist? - Context requirements — which files, APIs, or secrets are needed? - Complexity — which steps are risky? - Progress — what's done, what's next?
Installation
claude mcp add overture-mcp -- npx overture-mcp
Configuration
{
"mcpServers": {
"overture": {
"command": "npx",
"args": ["overture-mcp"]
}
}Capabilities
- Review and approve AI-generated plans before code execution
Overture renders the agent's plan as an interactive flowchart via `submit_plan` and waits for your approval through `get_approval`.
- Monitor execution progress in real time
watch nodes update status (`update_node_status`) as the agent runs, with visual indicators for pending, active, completed, and failed steps.
- Pause, resume, or re-run plan steps
use `check_pause` and `check_rerun` to control execution mid-flow without losing context.
- Resume past plans from history
call `get_resume_info` to reload a saved plan with all field values, branch selections, and attachments preserved.
- Modify plans dynamically during execution
insert, remove, or replace nodes via `request_plan_update` and review changes in the plan diff view.
Tags
- development
Related MCP servers
Context7 MCP
OfficialOfficial Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.
Chrome DevTools MCP
OfficialOfficial Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.
Mastra/mcp
OfficialClient implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
GitHub MCP Server
OfficialConnect your AI assistant to GitHub repositories, issues, pull requests, and search.