{
  "markdown": "# gate402-mcp\n\n[![x402 trust](https://x402.fuchss.app/badge.svg?resource=https%3A%2F%2Fgate402.app%2Fv1%2Fproxy)](https://x402.fuchss.app/provider/gate402.app)\n\nMCP server for **[Gate402](https://gate402.app)** — 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:\n\n| Tool | What it does | Price |\n|---|---|---|\n| `gate402_infer` | 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) |\n| `gate402_compute` | Rent metered GPU/CPU to run a container job; signed execution receipt | per-second |\n| `gate402_scrape` | Fetch any public URL, render JS, strip nav/ads → clean LLM-ready Markdown | $0.002 |\n| `gate402_scrape_stealth` | Cloudflare/anti-bot fetch via residential proxies + CAPTCHA solving → clean Markdown | $0.05 |\n| `gate402_minify` | Compress text to cut downstream LLM token spend (~40%) | $0.005 / 10k tok |\n| `gate402_dedup` | Semantic vector-cache lookup (exact + cosine) | $0.001 hit / $0.003 miss |\n| `gate402_onchain` | On-chain wallet/token intel on Base (balances, EOA/contract, tx count, token metadata) | $0.01 |\n| `gate402_dex` | Live DEX price / liquidity / 24h volume for a Base token | $0.01 |\n| `gate402_news` | Recent news headlines + bull/bear sentiment for a ticker/topic | $0.02 |\n| `gate402_edgar` | Latest SEC EDGAR filings (10-K/10-Q/8-K) for a US ticker | $0.02 |\n| `gate402_token_risk` | Rug/tradeability verdict for a Base token (score + SAFE/CAUTION/AVOID; liquidity, honeypot sim, holder concentration) | $0.03 |\n| `gate402_momentum` | Momentum + order-flow signal for a Base token (RISING/FALLING + ACCUMULATION/DISTRIBUTION, honeypot-gated) | $0.02 |\n| `gate402_best_swap` | Best-execution intel: which DEX pool + estimated price impact for a trade size | $0.02 |\n| `gate402_launches` | Radar of the freshest Base token launches, lightly pre-screened | $0.02 |\n\n…plus three **free** tools that run **locally in this process** (pure compute — no payment, no key, no network):\n\n| Tool | What it does |\n|---|---|\n| `gate402_token_count` | Estimate the token count of a string (budget your context window) |\n| `gate402_html_to_md` | Convert an HTML string you already have into clean Markdown |\n| `gate402_json_repair` | Coerce malformed / LLM-mangled JSON into valid JSON |\n\n### GPU marketplace\n\nGate402 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.\n\n| Tool | What it does |\n|---|---|\n| `gate402_market_infer` | 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) |\n| `gate402_providers` | **Free.** Browse active providers — model, per-call price, reliability |\n| `gate402_become_provider` | **Free.** List your own GPU and earn 85%/call — returns the exact sign-message + registration request |\n\n## How billing works\n\nOn 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](https://gate402.app/ops/billing/checkout)).\n\nThe payment *is* the auth — there are no accounts to create.\n\n## Install\n\n```bash\nnpm install -g gate402-mcp\n```\n\nOr run without installing via `npx gate402-mcp`.\n\n## Configure your MCP client\n\n### Claude Desktop / Claude Code\n\nAdd to your MCP config (`claude_desktop_config.json`, or `claude mcp add`):\n\n```json\n{\n  \"mcpServers\": {\n    \"gate402\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"gate402-mcp\"]\n    }\n  }\n}\n```\n\n### Cursor / Cline / Windsurf\n\nSame shape — point the MCP server `command` at `npx -y gate402-mcp`.\n\n### Agent frameworks (LangChain, CrewAI, LlamaIndex)\n\ngate402 is a standard stdio MCP server, so any framework with an MCP adapter can load all 17 tools:\n\n**LangChain / LangGraph** (`langchain-mcp-adapters`):\n```python\nfrom langchain_mcp_adapters.client import MultiServerMCPClient\nclient = MultiServerMCPClient({\"gate402\": {\"command\": \"npx\", \"args\": [\"-y\", \"gate402-mcp\"], \"transport\": \"stdio\"}})\ntools = await client.get_tools()   # feed into your agent\n```\n\n**CrewAI** (`MCPServerAdapter`):\n```python\nfrom crewai_tools import MCPServerAdapter\nfrom mcp import StdioServerParameters\nparams = StdioServerParameters(command=\"npx\", args=[\"-y\", \"gate402-mcp\"])\nwith MCPServerAdapter(params) as tools:\n    ...  # pass tools to your Crew\n```\n\n**LlamaIndex** (`McpToolSpec`):\n```python\nfrom llama_index.tools.mcp import BasicMCPClient, McpToolSpec\ntools = McpToolSpec(client=BasicMCPClient(\"npx\", args=[\"-y\", \"gate402-mcp\"])).to_tool_list()\n```\n\nOnce wired, the agent calls the tools autonomously; the free-credit key is claimed on first use, and paid tools draw down from it.\n\n## Environment variables\n\n| Var | Default | Purpose |\n|---|---|---|\n| `GATE402_API_KEY` | _(unset)_ | Use a funded account instead of the free tier. |\n| `GATE402_BASE_URL` | `https://gate402.app` | Override the gateway (self-hosting / testing). |\n| `GATE402_CONFIG_DIR` | `~/.gate402-mcp` | Where the cached free key is stored. |\n\n## Develop\n\n```bash\nnpm install\nnpm run build\nnpm start          # or: npm run dev\n```\n\n## License\n\nMIT\n",
  "bytes": 5621,
  "sha": "8dd0f82e05a6b222825d94b89b1560db30f947bbe131abf0673432eda1db191a",
  "repo_slug": "pgalyen1987/gate402-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pgalyen1987_gate402_mcp_b59c04d0/readme"
}