About Lium Docs
Lium Docs is a skill for coding agents that guides GPU rental and pod management on Lium. It includes CLI and SDK references and, when installed as a Claude Code plugin, adds an MCP server for GPU prices, rental links, and documentation search.
Key features
- 01Agent skill for Lium GPU rentals
- 02Instructions for pod management
- 03On-demand CLI and SDK references
- 04Installable in Claude Code, Cursor and Codex
- 05Installer for agent skill directories
Use cases
- 01Guide an agent through renting GPUs
- 02Help manage Lium pods
- 03Look up CLI or SDK usage
- 04Search Lium documentation and GPU prices
MCP support
The Claude Code plugin also configures Lium's hosted MCP server at https://docs.lium.io/mcp. It provides live GPU prices, rental links, and documentation search.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://docs.lium.io/mcpclaude mcp add --transport http datura-ai-lium-docs https://docs.lium.io/mcp{"mcpServers":{"datura-ai-lium-docs":{"type":"http","url":"https://docs.lium.io/mcp"}}}Open in Cursor{"servers":{"datura-ai-lium-docs":{"type":"http","url":"https://docs.lium.io/mcp"}}}Open in VS Code{"mcpServers":{"datura-ai-lium-docs":{"type":"http","url":"https://docs.lium.io/mcp"}}}{"mcpServers":{"datura-ai-lium-docs":{"serverUrl":"https://docs.lium.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
2| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | Maximum number of results to return (default 10, max 50) |
| query | string | Yes | Search query |
| audience | enum | No | Filter results to a specific audience sectionproviders | validators | pod-users | developers |
Details
From the project READMElium-skill
The lium agent skill — teaches an AI coding agent to rent GPUs and manage pods
on Lium, agent-first compute: a GPU rental platform.
Install
npx skills add Datura-ai/lium-skill --skill lium
Works in any agent that supports the Agent Skills standard — Claude Code, Cursor, Codex and others.
In Claude Code, install it as a plugin, which also adds the Lium MCP server
(https://docs.lium.io/mcp: live GPU prices, rent links, docs search):
/plugin marketplace add Datura-ai/lium-skill
/plugin install lium@lium
Without node, install into the agent skill directories directly:
curl -fsSL https://lium.io/agents/install.sh | bash
The installer writes SKILL.md and references/ into ~/.claude/skills/lium/,
~/.cursor/skills/lium/ and ~/.codex/skills/lium/; it takes --claude-only,
--cursor-only, --codex-only, --force (overwrite without a backup) and
-h. LIUM_SKILL_VERSION is the git ref the files are fetched from (default
main); the repository has no tags yet, so pin a commit sha until one exists.
The skill drives the lium CLI, so install that too:
curl -fsSL https://lium.io/install.sh | bash
lium init
What is in here
| Path | Purpose |
|---|---|
lium/SKILL.md | The skill itself — frontmatter plus agent instructions |
lium/references/ | CLI and SDK references, loaded on demand |
agents/install.sh | Source of lium.io/agents/install.sh (lium.io redirects to the raw file on main) |
.claude-plugin/ | Claude Code plugin and marketplace manifests: the lium skill plus the MCP server in .mcp.json |
llms.txt | Short discovery index for agents |
llms-full.txt | Self-contained reference, generated from the files above |
scripts/build-llms-full.sh | Generates llms-full.txt (SKILL.md without frontmatter + both references) |
examples/benchmarks/ | Reproducible GPU benchmarks run on Lium pods, with raw results (vLLM serving, 23 Sep 2026) |
chrome-extension/ | "Lium GPU Prices" Chrome extension: popup with live GPU prices from lium.io/pricing.json; store copy in STORE_LISTING.md, test with node --test chrome-extension/prices.test.mjs |
server.json | MCP Registry entry io.github.Datura-ai/lium-gpu-cloud for the hosted MCP endpoint https://docs.lium.io/mcp (live GPU prices and rent links, docs search; replaces the old lium-docs name); a change on main publishes it (bump version) |
.github/CODEOWNERS, .github/REVIEWING.md | Who reviews each path and how |
lium.io/llms.txt and lium.io/llms-full.txt are served from this repo's main.
Editing
llms-full.txt is generated. After changing lium/SKILL.md or anything under
lium/references/, regenerate and commit it in the same change — the
check-drift job (.github/workflows/check-llms-full.yml)
regenerates the file on every PR, push to main and merge-queue run and fails
on any difference:
./scripts/build-llms-full.sh
Links
- Docs: https://docs.lium.io
- CLI: https://github.com/Datura-ai/lium
- PyPI: https://pypi.org/project/lium.io/
License
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.