Skip to main content

lunaris-mcp

Lunaris MCP server — no Rust toolchain required.

Each wheel ships a prebuilt lunaris-mcp binary for your platform. uvx resolves the correct wheel automatically; the binary is exec'd via python -m lunaris_mcp.

Quick Start

uvx lunaris-mcp --help

via pip

pip install lunaris-mcp
lunaris-mcp --help

Configure as an MCP server

Claude Code (~/.claude.json)

{
  "mcpServers": {
    "lunaris": {
      "command": "uvx",
      "args": ["lunaris-mcp"]
    }
  }
}

Or using npx:

{
  "mcpServers": {
    "lunaris": {
      "command": "npx",
      "args": ["-y", "@pilotspace/lunaris-mcp"]
    }
  }
}

Codex (~/.codex/config.toml)

[mcp_servers.lunaris]
command = "uvx"
args    = ["lunaris-mcp"]

Supported Platforms

Platform Wheel tag
Linux x86_64 manylinux_2_28_x86_64
Linux arm64 manylinux_2_28_aarch64
macOS x86_64 macosx_12_0_x86_64
macOS arm64 (M1/M2/M3) macosx_12_0_arm64
Windows x64 win_amd64

Requirements

  • Python 3.11+
  • No Rust toolchain required
  • uv (recommended) or pip

If the binary is missing

If the binary is absent from the wheel (local dev, custom build), the lunaris-mcp entry point will print a clear error and suggest a source build:

cargo install --git https://github.com/pilotspace/lunaris lunaris-mcp

lunaris-mcp is not on crates.io — it links lunaris-memory-service, which carries a vendor/ path dependency and is therefore publish = false, and crates.io rejects a crate with unpublished dependencies. Plain cargo install lunaris-mcp will fail.

Air-gap / offline

For offline environments, either extract the prebuilt lunaris-mcp-<target>.tar.gz from a GitHub release (attached from 0.6.1 onward), or build from a checkout (needs Rust 1.94, cmake, and a C++ compiler for llama.cpp):

git clone --recurse-submodules https://github.com/pilotspace/lunaris
cd lunaris && cargo build --release -p lunaris-mcp
# binary at target/release/lunaris-mcp

Then use the lunaris-mcp binary directly.

Full integration guide

See docs/integration/claude-code.md and docs/integration/codex.md for complete configuration examples, environment variables, and troubleshooting.

Metadata

Release files for lunaris-mcp 0.8.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for lunaris-mcp 0.8.0
File Actions
lunaris_mcp-0.8.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for lunaris_mcp-0.8.0-py3-none-win_amd64.whl
lunaris_mcp-0.8.0-py3-none-manylinux_2_28_x86_64.whl Python 3 none Linux glibc 2.28+ x86-64 Details for lunaris_mcp-0.8.0-py3-none-manylinux_2_28_x86_64.whl
lunaris_mcp-0.8.0-py3-none-manylinux_2_28_aarch64.whl Python 3 none Linux glibc 2.28+ ARM64 Details for lunaris_mcp-0.8.0-py3-none-manylinux_2_28_aarch64.whl
lunaris_mcp-0.8.0-py3-none-macosx_12_0_x86_64.whl Python 3 none macOS 12.0+ x86-64 Details for lunaris_mcp-0.8.0-py3-none-macosx_12_0_x86_64.whl
lunaris_mcp-0.8.0-py3-none-macosx_12_0_arm64.whl Python 3 none macOS 12.0+ ARM64 Details for lunaris_mcp-0.8.0-py3-none-macosx_12_0_arm64.whl

Total release size: 35.9 MB

Release files / lunaris_mcp-0.8.0-py3-none-win_amd64.whl

Download URL lunaris_mcp-0.8.0-py3-none-win_amd64.whl
Size 7.2 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
d05571a949133b970c42232d4ec2c0f99a7454f8ff8d0a25bdbe2e7a936f7d35
BLAKE2b-256 checksum
How to use checksums
2e8275f12000ab679c463e2e34845922eb2de98daaeedba7d4f8ab179bb32937
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via maturin/1.15.0

Release files / lunaris_mcp-0.8.0-py3-none-manylinux_2_28_x86_64.whl

Download URL lunaris_mcp-0.8.0-py3-none-manylinux_2_28_x86_64.whl
Size 7.5 MB
Tags Linux glibc 2.28+ x86-64 Python 3
SHA-256 checksum
How to use checksums
6b31d1c36bc602e2875c88f17e998e098af7a27d3458cf34b81d6ddd18d10822
BLAKE2b-256 checksum
How to use checksums
ad16522cf43a7fb543417dd0e20bfa4977a71f7f9010230bbf8638111bc3fe5b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via maturin/1.15.0

Release files / lunaris_mcp-0.8.0-py3-none-manylinux_2_28_aarch64.whl

Download URL lunaris_mcp-0.8.0-py3-none-manylinux_2_28_aarch64.whl
Size 6.9 MB
Tags Linux glibc 2.28+ ARM64 Python 3
SHA-256 checksum
How to use checksums
4404898944b1b8fc2c77466fea2384069717cda1518a1e59ca98b0b94301024d
BLAKE2b-256 checksum
How to use checksums
ab9fd1a759d5fad725817ee15f6454f9bfa99c418af6ae29c72c4d847ca374ea
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via maturin/1.15.0

Release files / lunaris_mcp-0.8.0-py3-none-macosx_12_0_x86_64.whl

Download URL lunaris_mcp-0.8.0-py3-none-macosx_12_0_x86_64.whl
Size 7.4 MB
Tags Python 3 macOS 12.0+ x86-64
SHA-256 checksum
How to use checksums
f849d5b1fc8eb1edc56bad1c826a3d33685cee4101711d068d7cdbf2d0edcab5
BLAKE2b-256 checksum
How to use checksums
334d608216ecd8dc90a13840c017596fe80c2e3f2a8ba8ef8bf99fb9a85c89ce
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via maturin/1.15.0

Release files / lunaris_mcp-0.8.0-py3-none-macosx_12_0_arm64.whl

Download URL lunaris_mcp-0.8.0-py3-none-macosx_12_0_arm64.whl
Size 6.8 MB
Tags Python 3 macOS 12.0+ ARM64
SHA-256 checksum
How to use checksums
3df05dd0648ddb267b74944dd836404851d84f2606647fd23b2ff60a17724a8b
BLAKE2b-256 checksum
How to use checksums
c2b8222f0bb45cd3379eac8872f6f058ea8fbe2291039ab7722185ab62fa5335
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via maturin/1.15.0

Security for lunaris-mcp 0.8.0

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page