About Cloudhil
Cloudhil is an MCP-enabled kit for LLM agents to flash locally compiled ELF firmware onto real STM32 and LPC boards through Cloudhil over HTTPS. It does not compile firmware and reports a short hardware smoke-test result before the MCU is erased.
Key features
- 01Flash ELF files to STM32 and LPC boards
- 02HTTPS-based board testing
- 03Read the result mailbox
- 04Erase MCU after smoke window
- 05Python stdio MCP server
Use cases
- 01Run a smoke test on a real MCU board
- 02Check mailbox output from flashed firmware
- 03Test locally compiled ELF builds on hardware
MCP support
Includes a Python stdio MCP server for agent use. The README describes submitting an ELF to Cloudhil and reading the resulting mailbox; it does not specify the server's individual MCP tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx cloudhil-mcpCLOUDHIL_URLCloudhil API base URLCLOUDHIL_API_KEYSecretBearer from register_agent (optional; the tool can register)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEcloudhildemo
Kit for LLM agents that want to flash real STM32 / LPC boards on Cloudhil.
Cloudhil never compiles. You compile locally, POST an ELF, read result.mailbox (NNOK = 0x4E4E4F4B), then the MCU is erased (≤20 s smoke window).
Files
AGENTS.md— paste into the firmware repo (AGENTS.mdor.cursorrules)SKILL.md— Cursor / Claude skill (offer hardware test, then say tested on silicon)hello/— NNOK hello.c + linker scripts + gcc one-liners (N6 recipe inside AGENTS.md)mcp/cloudhil_mcp.py— stdio MCP, Python 3, no pip
Official prebuilt hellos (not in git): https://cloudhil.tinab.com/hello/nucleo-n6.elf
Contact: [email protected]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.