> For the complete documentation index, see [llms.txt](https://rootai.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://rootai.gitbook.io/docs/mcp/pro.md). # Pro ## Edge MCP Pro Pro is the premium tier of the Edge MCP at rootedge.ai. Discovery is free, premium signal tools cost a small USDC payment per call, settled on-chain via [x402](https://x402.org). No signup, no API key, no subscription. Bring a wallet with USDC, that's it. **Network:** Base mainnet. **Settlement:** USDC via x402, gas sponsored ### Endpoint ``` https://mcp.rootedge.ai/pro ``` ### Premium tools (paid) | Tool | Price | Returns | | ---------------------- | ---------: | ------------------------------------------------------------- | | `signals_recent` | $0.01 USDC | Latest Hyperliquid signals, graded A/B/C/D, multi-factor | | `signals_by_coin` | $0.01 USDC | Historical signals for one coin (`BTC`, `xyz:NATGAS`, etc.) | | `signals_stream_since` | $0.05 USDC | Long-poll up to 30s for new signals since a unix-ms timestamp | Signals cover Hyperliquid crypto perps **plus** HIP-3 `xyz` stocks / RWA / FX / commodities. Each signal carries grade, normalized score, percentile rank, liquidity tier, multi-factor flags, directional bias, and a human-readable headline. ### Free relayed tools All 88 tools from the public Edge MCP are mirrored here at no cost: `hyperliquid_*`, `dex_*`, `base_*`, `edge_*`, `stock_market_cissor_*`, `binance_*`. Use Edge MCP Pro as a one-stop endpoint, or hit the public MCP directly at `https://mcp.rootedge.ai/mcp` for the free ones. Same data either way. ### Payment details | Field | Value | | ----------- | --------------------------------------------------- | | Network | `eip155:8453` (Base mainnet) | | Asset | USDC (`0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913`) | | Scheme | `exact` (EIP-3009 `transferWithAuthorization`) | | Pay to | `0x09F2830636F2Edf71F7cA929dCC20cC1F161C897` | | Facilitator | Coinbase CDP | ### Browse tools (free, no wallet) ```bash curl -s https://mcp.rootedge.ai/pro \ -H "content-type: application/json" \ -H "accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize", "params":{"protocolVersion":"2025-11-25","capabilities":{}, "clientInfo":{"name":"curl","version":"1"}}}' ``` ### Call a paid tool x402 on MCP carries the payment in the `tools/call` **`_meta`** field under the key `x402/payment` — **not** in an HTTP header. (HTTP-header-only x402 clients like `x402-fetch` / `x402-axios` will not authenticate against this endpoint.) Standard three-step flow any x402-aware MCP client follows automatically: 1. Call the tool with no payment → server returns 402-equivalent error with structured `accepts[]` requirements. 2. Sign an EIP-3009 `transferWithAuthorization` matching one of the `accepts` entries (USDC, Base mainnet, the price + recipient above). 3. Retry the same call with the signed payload attached as `_meta["x402/payment"]` → server verifies, executes the tool, the facilitator settles on-chain, the result is returned in the response. #### Python reference A minimal working client using the MCP Python SDK plus `x402` for the signing step: ```python from mcp import ClientSession from mcp.client.streamable_http import streamablehttp_client from x402.client import x402Client from x402.mcp.constants import MCP_PAYMENT_META_KEY from x402.mechanisms.evm.exact import register_exact_evm_client from x402.mechanisms.evm.signers import EthAccountSigner from x402.schemas.payments import PaymentRequired from eth_account import Account acct = Account.from_key(PRIVATE_KEY) client = x402Client() register_exact_evm_client(client, EthAccountSigner(acct)) async with streamablehttp_client("https://mcp.rootedge.ai/pro") as (r, w, _): async with ClientSession(r, w) as session: await session.initialize() # 1. Call without payment, get 402 r1 = await session.call_tool("signals_recent", {"limit": 5}) pr = PaymentRequired.model_validate(r1.structuredContent) # 2. Sign EIP-3009 payload payload = await client.create_payment_payload(pr) # 3. Retry with payment in _meta r2 = await session.call_tool( "signals_recent", {"limit": 5}, meta={MCP_PAYMENT_META_KEY: payload.model_dump(by_alias=True, exclude_none=True)}, ) print(r2.structuredContent) # graded signals ``` ### Signal wire shape ```json { "ts": 1781319548748, "asset_class": "crypto", "coin": "BTC", "base": "BTC", "side": "long", "bias": "bullish", "headline": "Fresh longs piling in — open interest +6.8% as price runs 8.2%...", "kind": "OI_SHIFT", "grade": "A", "score_normalized": 78, "score_raw": 14.7, "percentile": 94, "tier": "DEEP", "risk": 32, "abnormality": 88, "confirmation": 71, "tradeability": 80, "context_score": 62, "flags": ["OI_SURGE", "FUNDING_FLIP", "FAST_MOVE"], "metrics": { "mid": 67234.5, "oi_usd": 1.2e9, "oi_z": 3.1, "vol_z": 2.4, "oi_change_pct": 6.8, "funding_hourly": -0.0001, "move_24h_pct": 8.21 } } ``` --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://rootai.gitbook.io/docs/mcp/pro.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.