Unified Airdrop Eligibility: Bridging Browser Tools and LLMs via MCP
These articles are AI-generated summaries. Please check the original sources for full details.
Paste a wallet, get a personal airdrop verdict — and call the same logic from any LLM
Weston G has released a dual-surface tool that evaluates 14 hand-verified on-chain rules for airdrop eligibility. The system bridges a browser-based frontend with a Model Context Protocol (MCP) server to ensure consistent results across all interfaces.
Why This Matters
Traditional airdrop directories often provide low-signal data by matching broad chain activity rather than specific contract interactions. This tool addresses the signal-to-noise problem by utilizing client-side RPC fanning and a single source of truth for rules, preventing data drift. By exposing this logic via MCP, developers can integrate high-fidelity on-chain verification directly into LLM workflows like Claude or Cursor, bypassing the need for fragile web scraping.
Key Insights
- The system evaluates 14 rules against 42 curated entries, resolving in 2-5 seconds for complex wallets like vitalik.eth.
- JSON-RPC batching optimizes performance by bundling eth_getTransactionCount and eth_call requests into a single POST per EVM chain.
- A single-file source of truth (eligibility-rules.json) is shared between the Astro web frontend and the MCP serverless function to ensure zero drift.
- The MCP tool returns structured JSON verdicts categorized into eligible, partial, skip, manual, and unavailable buckets for LLM consumption.
Working Examples
Calling the check_eligibility tool via the MCP JSON-RPC interface
curl -s -X POST https://web3-discover.vercel.app/api/mcp \
-H 'content-type: application/json' \
-d '{
"jsonrpc": "2.0",
"id": 7,
"method": "tools/call",
"params": {
"name": "check_eligibility",
"arguments": { "evm": "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045" }
}
}'
Configuration for integrating the tool into Claude Desktop or Cursor
{
"mcpServers": {
"web3-discover": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://web3-discover.vercel.app/api/mcp"]
}
}
}
Prebuild script ensuring the MCP server and browser tool share the same rule registry
fs.copyFileSync(
path.join(ROOT, 'src/data/eligibility-rules.json'),
path.join(ROOT, 'api/_eligibility-rules.json'),
);
Practical Applications
- Integrating wallet eligibility checks into LLM chats (Claude/Cursor) to provide real-time decision support for crypto users.
- Using browser-side RPC calls to verify on-chain status without signature requirements or server-side address logging.
- Pitfall: Relying on broad ‘chain usage’ metrics which leads to high false-positive rates in airdrop discovery.
- Pitfall: Manual HTML scraping of directory sites which results in flaky data integration for automated agents.
References:
Continue reading
Next article
Sakana AI and NVIDIA Introduce TwELL: 20.5% Faster LLM Inference via Unstructured Sparsity
Related Content
Side-by-Side UCP Store Comparison: Benchmarking Agent-Ready Commerce
UCPChecker launches a side-by-side comparison tool to benchmark agent-ready commerce capabilities, using set operations to diff capabilities, transports, and payment handlers across domains.
Interfacing 3D Printers with LLMs: Building a Secure MCP Server for the Flashforge AD5M
Engineer Nic Lydon developed kiln-mcp, a TypeScript server bridging Claude to a 3D printer via dual HTTP and legacy TCP APIs, featuring local image-to-STL generation.
Grounding LLMs in Maritime Data: Using MCP for Port Intelligence
Leveraging the Model Context Protocol (MCP) to generate port briefings using real-time data from 16 VesselAPI maritime tools.