MCP-Server-Lighter
Exposes Lighter DEX data (volume, points, rank, liquidity, airdrop eligibility) as MCP tools, letting LLM agents query wallet farming stats in natural language. Read-only, no keys required, works with Claude, Cursor, and Cline.
README
MCP-Server-Lighter
MCP server for Lighter โ a Model Context Protocol server that lets Claude, Cursor and Cline query Lighter (lighter.xyz) volume, points, rank and airdrop eligibility in natural language. Read-only โ public endpoints only, no keys. Unofficial community project, not affiliated with Lighter. <div align="center">
๐ MCP Server โ Lighter
MCP server for Lighter โ volume, points, rank & airdrop eligibility as tools for LLM agents.
Ask Claude / Cline / Cursor: "How close is my Lighter wallet to the SILVER airdrop tier?" โ and get a real answer.
</div>
๐ Overview
MCP Server โ Lighter is a Model Context Protocol server for the Lighter DEX API that exposes trading volume, campaign points, leaderboard rank, liquidity and airdrop eligibility as MCP tools for any MCP-compatible LLM agent. It works with Claude Desktop, Cursor, and Cline โ an Ethereum L2 perpetual futures DEX integration that lets you query Lighter volume, points, rank, and airdrop eligibility from Claude in natural language, built on the official MCP Python SDK.
Instead of copy-pasting wallet addresses into a web dashboard, your AI assistant calls the tools directly and reasons about your farming progress in plain language โ natural-language access to Lighter airdrop farming stats with structured tool outputs for AI agents and LLM workflows:
"You're at $142,800 campaign volume โ BRONZE tier, 95% of the way to SILVER ($150k). Keep your maker ratio above 50% and provide liquidity for 9 more days to also satisfy the liquidity criterion."
โ ๏ธ Read-only โ public endpoints only, no keys. The server exposes data tools only โ no trading, no signing.
โจ Tools exposed
| Tool | Returns |
|---|---|
get_volume |
Today / 7-day / 30-day / campaign volume + maker/taker split. |
get_points |
Estimated campaign points with maker-bonus & liquidity multiplier breakdown. |
get_rank |
Leaderboard position with daily delta. |
get_markets |
Available Lighter orderbook markets. |
get_liquidity |
Days of liquidity provided + tier. |
get_eligibility |
Airdrop tier snapshot โ satisfied vs. missing criteria. |
list_tasks |
Farming task checklist with completion state. |
Each tool returns typed JSON the agent can reason over.
๐ Quick start
git clone https://github.com/isabelpapaya/mcp-server-lighter.git
cd mcp-server-lighter
pip install -r requirements.txt
python main.py --demo # stdio transport, bundled demo wallet
Or use the one-click launchers (they unpack a bundled standalone interpreter on first run):
run.bat :: Windows
chmod +x run.sh && ./run.sh # Linux / macOS
๐ Connect your client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"lighter": {
"command": "python",
"args": ["C:\\path\\to\\mcp-server-lighter\\main.py", "--demo"]
}
}
}
Cline / Cursor / Continue
Point the client at the server over stdio with the same command โ see your client's MCP settings page.
๐งช Try the tools headlessly
python main.py --tool get_eligibility --wallet 0x9fโฆc310 --demo
๐๏ธ Project layout
mcp-server-lighter/
โโโ main.py # Entry point (unpacks bundled runtime on first launch)
โโโ mcp_lighter/ # Host package
โ โโโ __main__.py # `python -m mcp_lighter` entry (argparse + server bootstrap)
โ โโโ server.py # FastMCP tool definitions
โ โโโ config.py # Config loader (TOML)
โ โโโ core/ # models, analytics, mock data
โโโ base/ # Runtime support library
โโโ requirements.txt
โโโ run.bat / run.sh # One-click launchers
โโโ release/ # Pre-compiled binaries (planned)
โ๏ธ Configuration
# ~/.lighter-mcp/config.toml
[network]
rpc = "https://mainnet.optimism.io"
[campaign]
points_per_dollar = 2.0
maker_bonus_pct = 0.20
liquidity_multiplier = 1.25
tiers = [
{ name = "BRONZE", volume = 50000 },
{ name = "SILVER", volume = 150000 },
{ name = "GOLD", volume = 300000 },
{ name = "PLATINUM", volume = 600000 },
]
๐ Security
- Read-only. Data tools only โ no order placement, no signing, no private keys.
- No telemetry. Queries go to the configured public RPC; nothing is phone-homed.
โ FAQ
<details> <summary><b>What is MCP?</b></summary>
The Model Context Protocol โ an open standard for connecting LLMs to external tools and data sources. See modelcontextprotocol.io. </details>
<details> <summary><b>Does the server trade on my behalf?</b></summary>
No. It exposes read-only data tools. An LLM can summarise your farming progress and suggest next steps, but it cannot place orders through this server. </details>
<details> <summary><b>Is this affiliated with Lighter or Anthropic?</b></summary>
No. Independent, unofficial community project. Lighter is a third-party protocol; MCP is an open standard. </details>
โ ๏ธ Disclaimer
This is an unofficial community project, not affiliated with, endorsed by, or sponsored by Lighter XYZ or Anthropic. Provided for research purposes โ not financial advice.
๐ License
MIT โ see LICENSE.
<div align="center"><sub>Bring Lighter on-chain data into your LLM agent.</sub></div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.