FRENES

Smart home and IoT · MCP server

Kiln: MCP server, setup and security

Kiln is an open-source MCP server that lets an AI agent design, slice, queue and monitor 3D prints with failure recovery. Its repository has 219 stars and its last commit is from October 24, 2026 and it is licensed under AGPL-3.0.

Actively maintainedNeeds secrets

What Kiln does

According to its repository: “Run 3D printers end to end: design, slice, queue, monitor via camera and recover from failures over OctoPrint, Moonraker/Klipper, PrusaLink or USB.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Kiln is listed under Smart home and IoT, a category of 34 servers in the directory, where it ranks #6 by stars.

Topics declared by the repository: 3d-printing, ai-agents, bambu-lab, klipper, moonraker, octoprint.

Installing and connecting Kiln

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python. Listed systems: macOS, Windows, Linux.

The registry lists one secret variable to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Kiln:

  • Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 10, 2026, the codeofaxel/Kiln repository has 219 stars and 21 forks, with 0 open issues. It has more stars than 79% of the servers in the directory. It received changes this month. Version published in the registry: 1.5.0 (October 21, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Ha MCPHa MCP : 5.2K5.2KStack chanStack chan : 1.8K1.8KTapo MCPTapo MCP : 863863BagelBagel : 399399Bambu Printer MCPBambu Printer MCP : 233233KilnKiln : 219219Embedded debugger MCPEmbedded debugger MCP : 210210Esp MCPEsp MCP : 157157
GitHub stars of the most followed servers in the category (log scale); Kiln in orange. Checked October 25, 2026.

Verdict

Kiln is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Widely followed: 219 stars
  • Listed in the official MCP registry

Limitations

  • Requires an API key or token

Avoid if…

  • You do not want to give credentials to an agent

Frequently asked questions

How do I install Kiln?

Kiln is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of codeofaxel/Kiln.

Is Kiln free?

The code is published under the AGPL-3.0 licence and can be used free of charge. It needs an API key: the service it connects to may be paid.

Is Kiln safe?

Points to watch: secrets. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by codeofaxel on GitHub. Check who maintains it before giving it access.

What are the alternatives to Kiln?

In the same category: Ha MCP, Stack chan, Bagel, and Tapo MCP.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score