conductor vs mcp-use
Two of the top projects in Agent and MCP starters, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
conductor
Durable workflow engine that orchestrates microservices and LLM agents from JSON
mcp-use
TypeScript framework for building MCP servers with React Views and an Inspector
Verdict
conductor ranks higher, 91 to 87. Of the 4 score parts we measure for both, conductor leads on 2, mcp-use on 1 and 1 is even.
- Adoptionconductor leads by 13 points, 93 to 80.
- FreshnessEven at 100.
- Maintenancemcp-use leads by 8 points, 94 to 86.
- Agent-readyconductor leads by 25 points, 70 to 45: a wide gap.
Pick conductor if you are
Backend teams needing durable orchestration for services and AI agent loops
- Every step is persisted, with retry, restart, rerun, pause and terminate controls on executions
- Workflows are versioned JSON; running executions stay pinned to the version they started on
Pick mcp-use if you are
TypeScript developers building MCP servers and ChatGPT or Claude apps
- Zod schemas flow from tool input and output into React View props
- Built-in Inspector, tunnel (mcp-use dev --tunnel) and View screenshot CLI
| What we compare | conductor | mcp-use |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 93, widely used | 80, popular |
| Momentum | Not scored for this kind | Not scored for this kind |
| Freshness | 100, active | 100, active |
| Maintenance | 86, healthy | 94, healthy |
| Agent-ready | 70, partly | 45, minimal |
| Facts from GitHub and the README | ||
| Stars | 32.5k | 10.9k |
| License | Apache-2.0 (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Oct 2026 | Nov 2026 |
| Language | Java | TypeScript |
| Docker | Yes | No |
| GPU | Not stated | Not needed |
| arm64 or Apple Silicon | Mentioned | Not stated |
conductor
Conductor is a Java workflow orchestration server, originally from Netflix, that persists every task and runs versioned JSON workflow graphs. Workers in Java, Python, Go, JavaScript, C#, Ruby or Rust poll for tasks, while built-in tasks cover LLM chat, MCP tool discovery and calls, human approval, loops, forks and sub-workflows. It runs on Redis, Postgres or MySQL, with Elasticsearch or OpenSearch for indexing.
Who it is for: Backend teams needing durable orchestration for services and AI agent loops
Strengths
- Every step is persisted, with retry, restart, rerun, pause and terminate controls on executions
- Workflows are versioned JSON; running executions stay pinned to the version they started on
- Native LLM_CHAT_COMPLETE, LIST_MCP_TOOLS and CALL_MCP_TOOL tasks for agent loops
- Multiple persistence backends (Redis, Postgres, MySQL) and polyglot worker SDKs
Weaknesses
- Requires Java 25+ and a separate index store such as Elasticsearch or OpenSearch
- Orchestration is declarative JSON, not code, which suits some teams less than code-first engines
- Ruby and Rust SDKs are marked incubating
- Not a ready-made agent app; you build agents by composing workflow tasks
- Java, OpenAI (via llmProvider)
- Needs Java 25+, Node.js 16+ (CLI), Redis, Postgres or MySQL, Elasticsearch or OpenSearch
- Docker
mcp-use
mcp-use is a TypeScript framework for writing MCP servers with Zod-typed tools and React Views bound to those tools, so they render as interactive apps in ChatGPT and Claude. It ships a browser Inspector at /mcp/inspector, a headless CLI client with View screenshots, and tunneling for testing against hosted clients. It builds on the official TypeScript SDK v2 and deploys to Manufact or self-hosted.
Who it is for: TypeScript developers building MCP servers and ChatGPT or Claude apps
Strengths
- Zod schemas flow from tool input and output into React View props
- Built-in Inspector, tunnel (mcp-use dev --tunnel) and View screenshot CLI
- Scaffold via npx create-mcp-use-app gives a running server and Inspector
- MIT licensed; separate client, agent and Python packages exist
Weaknesses
- Benchmark comparisons in the README are published by the project itself
- Managed deploy, observability and evals tie into the commercial Manufact platform
- v2 is a breaking change; v1 projects need migration
- Server framework is TypeScript; Python support is a separate package
- TypeScript
- Needs Node.js, npm, zod, React
More in Agent and MCP starters
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.