mcp-use vs neuron-ai
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.
mcp-use
TypeScript framework for building MCP servers with React Views and an Inspector
neuron-ai
PHP framework for building LLM agents, RAG pipelines and workflows
Verdict
mcp-use ranks higher, 88 to 77. Of the 4 score parts we measure for both, mcp-use leads on 2, neuron-ai on 1 and 1 is even.
- Adoptionmcp-use leads by 37 points, 85 to 48: a wide gap.
- FreshnessEven at 100.
- Maintenanceneuron-ai leads by 5 points, 98 to 93.
- Agent-readymcp-use leads by 15 points, 45 to 30: a wide gap.
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
Pick neuron-ai if you are
PHP developers adding agents or RAG to Laravel, Symfony or plain PHP apps
- Provider switch is a one-line change across Anthropic, OpenAI, Gemini, Ollama, Bedrock and others
- Same Workflow component covers single agents and multi-agent flows with human approval
| What we compare | mcp-use | neuron-ai |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 85, widely used | 48, known |
| Freshness | 100, active | 100, active |
| Maintenance | 93, healthy | 98, healthy |
| Agent-ready | 45, minimal | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 11k | 2.2k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | Nov 2026 |
| Language | TypeScript | PHP |
| Docker | No | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Not stated | Not stated |
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
neuron-ai
Neuron is a Composer package that provides an Agent class with chat memory, tools, MCP connectors and structured output into PHP classes, plus a RAG class that takes a vector store and an embeddings provider. A separate Workflow component handles event-driven flows with human-in-the-loop. It supports 16 LLM providers, including Anthropic, OpenAI, Gemini, Ollama and AWS Bedrock.
Who it is for: PHP developers adding agents or RAG to Laravel, Symfony or plain PHP apps
Strengths
- Provider switch is a one-line change across Anthropic, OpenAI, Gemini, Ollama, Bedrock and others
- Same Workflow component covers single agents and multi-agent flows with human approval
- Ships agent skills and an MCP server so coding assistants can write Neuron code
- Built-in MySQL toolkit runs SELECT queries in read-only transactions
Weaknesses
- PHP only, requires PHP 8.1 or newer
- Read-only MySQL tool can still read anything the connection user can read
- README spends more space on newsletter and ecosystem than on internals
- RAG example depends on external services such as Pinecone and Voyage
- PHP, Anthropic, OpenAI, Azure OpenAI, OpenAI-compatible APIs
- Needs PHP ^8.1, Composer, LLM provider API key
- Docker
- env example file
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.