{"id":"overture","name":"Overture","homepage":"https://github.com/SixHq/Overture","repo_url":"https://github.com/SixHq/Overture","category":"developer-tools","subcategories":["ai-agent-tooling","mcp-server","visualization"],"tags":["mcp","ai-agents","flowchart","planning","cursor","claude-code","cline","visualization","workflow"],"what_it_does":"Overture is an open-source MCP server that intercepts AI coding agent planning phases and renders execution plans as interactive visual flowcharts in a web UI before code is written, allowing developers to inspect, enrich, and approve plans.","use_cases":["Visualizing an AI coding agent's full execution plan as an interactive flowchart before any code is written","Attaching context (files, API keys, documentation) to specific plan nodes to guide agent execution","Choosing between multiple proposed implementation approaches at decision branches","Monitoring real-time execution status (active/completed/failed) of each plan step"],"not_for":["Non-coding agent use cases (data analysis, general chat)","Headless or CI/CD agent pipelines where visual review is impractical","Teams that prefer agents to act without a review checkpoint"],"best_when":"A developer wants visibility and control over what an AI coding agent will do before it modifies the codebase, especially on complex multi-step tasks.","avoid_when":"Running agents in automated pipelines without a human reviewer, or when the overhead of plan approval slows down rapid iteration.","alternatives":["agentic-radar","langfuse","langsmith","weights-and-biases"],"af_score":74.2,"security_score":60.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:06.044157+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}