Llun-MCP - Architectural Context for Agents
Intro
Llun-MCP extends Llun into the world of agentic workflows through the Model Context Protocol (MCP). While the Llun CLI tool helps developers enforce architectural principles during coding, Llun-MCP gives agents the same advantage — ensuring they design and generate solutions that align with your architectural rules from the very beginning.
Rather than waiting until code is complete to lint and fix, Llun-MCP injects your team’s architectural principles directly into the agent’s reasoning loop. This prevents the kind of ad-hoc, inconsistent output that often plagues LLM-driven code generation, and minimises the need for post agent clean-up.
To achieve this, Llun-MCP exposes a single, simple tool: get_rules - which provides the agents with the user selected architectural rules defined by their chosen config tomls. Through encouraging agents to utilise this tool prior to beginning coding tasks, Llun-MCP ensures all agentic workflows begin with a complete understanding of the underlying principles the solution should adhere to. By utilising STDIO, Llun-MCP remains fully portable to all agentic workflows regardless of networking setups, choice of LLM, etc...
All of this makes Llun-MCP perfect for teams that want to:
- Use agents as coding assistants without sacrificing design consistency
- reduce cost of agentic coding activities by ensuring the first results produced are close to the teams agreed standards
- Utilise Llun CLI for architectural assessment
- ensure agent-powered high velocity development doesnt come with a sacrifice in maintainability
Quick Start
Installation
to use the server, the fastest way is to pip install it into a local environment:
uv pip install llun-mcp
or for those not yet ready to migrate to uv:
pip install llun-mcp
Basic Usage
To use the tool in CLaude Code, add the following to your config:
{
"mcpServers": {
"llun_architectural_rules": {
"command": "uvx",
"args": [
"llun-mcp"
]
}
}
}
References
Metadata
Release files for llun-mcp 1.5.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llun_mcp-1.5.3-py3-none-win_amd64.whl | Python 3 | none | Windows x86-64 | Details |
| llun_mcp-1.5.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl | Python 3 | none | Linux glibc 2.17+ x86-64 | Details |
| llun_mcp-1.5.3-py3-none-macosx_11_0_arm64.whl | Python 3 | none | macOS 11.0+ ARM64 | Details |
Total release size: 4.8 MB
Release files / llun_mcp-1.5.3-py3-none-win_amd64.whl
| Download URL | llun_mcp-1.5.3-py3-none-win_amd64.whl |
|---|---|
| Size | 1.5 MB |
| Tags | Python 3 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
c9a1994b880c13bd33d075037e2b21252c48c502811c3b6a828736825e021e44
|
|
BLAKE2b-256 checksum How to use checksums |
e62a0bdc6950f18f4663bcb64f609d82edd38ac7f05aa602c26d599c1a6f0ff0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.13
|
Release files / llun_mcp-1.5.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | llun_mcp-1.5.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 1.8 MB |
| Tags | Linux glibc 2.17+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
744956ef80b3b5c8719a789bb36b1c9fe3331253515be48b2504f5946b73d887
|
|
BLAKE2b-256 checksum How to use checksums |
42fe4f8a61a207114440b0fcb7f363004218638c01b2923db6bc860681505d31
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.13
|
Release files / llun_mcp-1.5.3-py3-none-macosx_11_0_arm64.whl
| Download URL | llun_mcp-1.5.3-py3-none-macosx_11_0_arm64.whl |
|---|---|
| Size | 1.5 MB |
| Tags | Python 3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
1d39675bfbb4d8be5831cebed8e8ccd5d8599bb40a46ee85000d12108afbb7d8
|
|
BLAKE2b-256 checksum How to use checksums |
e0f4c766de308542c82043e328666a2af1692983e078df5278b55f2c29ce610e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.13
|
Security for llun-mcp 1.5.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.