The mcp-gate402 server is a pay-per-call agent API toolkit (HTTP 402, USDC on Base) with a free tier on first use. It covers:
Web Scraping
gate402_scrape — Fetch any public URL, render JS, strip ads, return clean Markdown ($0.002)
gate402_scrape_stealth — Hardened headless fetch for bot-protected/JS-heavy pages ($0.05)
LLM Optimization
gate402_minify — Compress text to reduce token spend ~40% ($0.005/10k tokens)
gate402_dedup — Semantic vector-cache lookup (exact + cosine similarity) to avoid redundant LLM calls ($0.001 hit / $0.003 miss)
Free Local Utilities
gate402_token_count — Estimate token count for context budgeting (free)
gate402_html_to_md — Convert an HTML string to clean Markdown (free)
gate402_json_repair — Fix malformed/LLM-mangled JSON (free)
Base Blockchain & DeFi Intelligence
gate402_onchain — Wallet/token intel: balances, EOA/contract status, tx count, token metadata ($0.01)
gate402_dex — Live DEX price, liquidity, and 24h volume for a Base token ($0.01)
gate402_token_risk — Rug/tradeability verdict with SAFE/CAUTION/AVOID rating, honeypot simulation, holder concentration ($0.03)
gate402_momentum — Momentum & order-flow signals (RISING/FALLING, ACCUMULATION/DISTRIBUTION) ($0.02)
gate402_best_swap — Best DEX pool and estimated price impact for a given trade size ($0.02)
gate402_launches — Radar of fresh, lightly pre-screened Base token launches ($0.02)
Financial & News Data
gate402_news — Recent headlines with bull/bear sentiment for a ticker or topic ($0.02)
gate402_edgar — Latest SEC EDGAR filings (10-K, 10-Q, 8-K) for a US ticker ($0.02)
Allows CrewAI agents to use the MCP server's tools for web scraping, text compression, semantic caching, and free utilities, enabling agent-driven data collection and preprocessing.
Enables LangChain agents to access tools for web scraping, text minification, semantic dedup, and free utilities via the LangChain MCP adapter, facilitating LLM-ready data retrieval and optimization.
Supports LangGraph agents by providing MCP tools for scraping, minification, semantic caching, and free utilities, allowing integration into graph-based agent workflows.
MCP server for Gate402 — pay-per-call agent APIs over HTTP 402 (x402 / USDC on Base). Gives any MCP client a full toolkit with no signup and a free tier on first runs — GPU/CPU compute, open-model LLM inference, a GPU marketplace, a complete Base trading loop (discover → vet → read → execute), and web tools:
Tool | What it does | Price |
| Open-model LLM inference (Llama 3.1 8B/70B, Qwen 2.5, Mistral); billed on actual tokens, signed usage receipt | per-token (from $0.05/1M in) |
| Rent metered GPU/CPU to run a container job; signed execution receipt | per-second |
| Fetch any public URL, render JS, strip nav/ads → clean LLM-ready Markdown | $0.002 |
| Cloudflare/anti-bot fetch via residential proxies + CAPTCHA solving → clean Markdown | $0.05 |
| Compress text to cut downstream LLM token spend (~40%) | $0.005 / 10k tok |
| Semantic vector-cache lookup (exact + cosine) | $0.001 hit / $0.003 miss |
| On-chain wallet/token intel on Base (balances, EOA/contract, tx count, token metadata) | $0.01 |
| Live DEX price / liquidity / 24h volume for a Base token | $0.01 |
| Recent news headlines + bull/bear sentiment for a ticker/topic | $0.02 |
| Latest SEC EDGAR filings (10-K/10-Q/8-K) for a US ticker | $0.02 |
| Rug/tradeability verdict for a Base token (score + SAFE/CAUTION/AVOID; liquidity, honeypot sim, holder concentration) | $0.03 |
| Momentum + order-flow signal for a Base token (RISING/FALLING + ACCUMULATION/DISTRIBUTION, honeypot-gated) | $0.02 |
| Best-execution intel: which DEX pool + estimated price impact for a trade size | $0.02 |
| Radar of the freshest Base token launches, lightly pre-screened | $0.02 |
…plus three free tools that run locally in this process (pure compute — no payment, no key, no network):
Tool | What it does |
| Estimate the token count of a string (budget your context window) |
| Convert an HTML string you already have into clean Markdown |
| Coerce malformed / LLM-mangled JSON into valid JSON |
Gate402 also routes to third-party GPU/compute providers with escrow-on-success — the buyer is charged only if the provider delivers. Providers keep 85% of each call, paid out on-chain in USDC on Base.
Tool | What it does |
| LLM inference via the marketplace, routed to the cheapest healthy provider. x402-native (settles on-chain per call — needs an x402 client, not the free-tier key) |
| Free. Browse active providers — model, per-call price, reliability |
| Free. List your own GPU and earn 85%/call — returns the exact sign-message + registration request |
On first use the server self-claims a free-credit API key from Gate402 and caches it at ~/.gate402-mcp/key.json. Calls draw down that credit. When it runs out, tools return a top-up link instead of failing. To skip the free tier, set GATE402_API_KEY to a funded account (top up).
The payment is the auth — there are no accounts to create.
Related MCP server: Pylon MCP Server
npm install -g gate402-mcpOr run without installing via npx gate402-mcp.
Add to your MCP config (claude_desktop_config.json, or claude mcp add):
{
"mcpServers": {
"gate402": {
"command": "npx",
"args": ["-y", "gate402-mcp"]
}
}
}Same shape — point the MCP server command at npx -y gate402-mcp.
gate402 is a standard stdio MCP server, so any framework with an MCP adapter can load all 17 tools:
LangChain / LangGraph (langchain-mcp-adapters):
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({"gate402": {"command": "npx", "args": ["-y", "gate402-mcp"], "transport": "stdio"}})
tools = await client.get_tools() # feed into your agentCrewAI (MCPServerAdapter):
from crewai_tools import MCPServerAdapter
from mcp import StdioServerParameters
params = StdioServerParameters(command="npx", args=["-y", "gate402-mcp"])
with MCPServerAdapter(params) as tools:
... # pass tools to your CrewLlamaIndex (McpToolSpec):
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
tools = McpToolSpec(client=BasicMCPClient("npx", args=["-y", "gate402-mcp"])).to_tool_list()Once wired, the agent calls the tools autonomously; the free-credit key is claimed on first use, and paid tools draw down from it.
Var | Default | Purpose |
| (unset) | Use a funded account instead of the free tier. |
|
| Override the gateway (self-hosting / testing). |
|
| Where the cached free key is stored. |
npm install
npm run build
npm start # or: npm run devMIT
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
The web capability layer for AI agents: render, extract, DNS, SSL, WHOIS & more via x402.
x402-gated web extraction gateway. Tools: extract, extract_batch.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pgalyen1987/gate402-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server