Happy slice of mcp pizzaMCP.pizza

nano-manus

MCP.Pizza Chef: memodb-io

nano-manus is a compact MCP server implementation that brings core Manus features into the MCP ecosystem. With around 1000 lines of code, it supports loading MCP tools from Docker, npx, and Smithery. It enables plan-then-execute workflows by gathering agents, creating plans, and assigning jobs efficiently, making it ideal for orchestrating multi-agent tasks within MCP environments.

Use This MCP server To

Orchestrate multi-agent workflows with plan-then-execute logic Load MCP tools dynamically from Docker, npx, and Smithery Manage and assign tasks to agents in complex workflows Implement Manus-like agent coordination in MCP environments Develop lightweight MCP server solutions for agent orchestration

README

🐜 nano_manus

Implementing some features of Manus with MCP

Shows the Memobase Workflow

nano-manus

Features

  • Small: nano_manus is about 1000 LOC.
  • Using MCP: nano_manus supports loading MCP from docker, npx and Smithery
  • Plan-then-Execute: nano_manus will gather your agents, make the plans and then assign the correct jobs to your agents

Use Cases

nano-manus.mp4
  • Find all .py file and explain them to me
  • Give me the latest weather in SF in last 7 days and save it to csv

Welcome to give more use cases!

QuickStart

Setup

Env

Your .env should look like:

BRAVE_API_KEY=BSAxxxx
JINA_API_KEY=jina_xxxx
OPENAI_API_KEY=sk-proj-XXXXX

Run default nano-manus

uv sync
uv run examples/basic_planner.py

Abilities

  • Search Web (mcp/brave-search, jina-ai-mcp-server)
  • Local files operations (@wonderwhy-er/desktop-commander)
  • Execute codes and commands in your computer (@wonderwhy-er/desktop-commander)
  • (coming soon) Implementing CodeAct
  • (coming soon) Read .pdf, .doc
  • (coming soon) browser use
  • (coming soon) multi-model router (claude, qwen, deepseek...)

Known Issues

  • nano-manus is extremely unstable! My guess is gpt-4o is not that good at tool use.
  • Unable to exit: seem like some MCPs will cause the problems of unable to exit the program when all the tasks were done.
  • nano-manus will operate files and run command on the current dir of your local computer, make sure you don't run it on some important folders.

nano-manus FAQ

How does nano-manus implement Manus features?
nano-manus replicates core Manus functionalities such as plan-then-execute workflows within the MCP framework, enabling agent coordination.
What platforms can nano-manus load MCP tools from?
It supports loading MCP tools from Docker containers, npx packages, and Smithery integrations.
Is nano-manus suitable for large-scale deployments?
nano-manus is lightweight (~1000 LOC) and ideal for small to medium orchestration tasks but may require scaling for very large environments.
How does nano-manus handle task assignment?
It gathers available agents, formulates plans, and assigns jobs to the appropriate agents automatically.
What programming language is nano-manus built with?
nano-manus is implemented in Python, requiring version 3.11 or higher.
Can nano-manus integrate with other MCP servers or clients?
Yes, it is designed to interoperate within the MCP ecosystem, supporting standard MCP protocols.
Where can I find nano-manus documentation and examples?
Documentation and usage examples are available on its GitHub repository and PyPI page.