Skip to content
ScanHood logo

ScanHood MCP server

Which MCP servers are ScanHood's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-27

← Back to ScanHood

Whose server it is
  • Registry namexyz.scanhood/mcpverified in the MCP registry

The registry name sits under scanhood.xyz. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools22
  • Server calls itselfscanhood
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 299 ms.

Should an agent connect itConnect it, with care
  • Its tools do every use case we checked: scan token contracts for honeypot and rug risk; check whether liquidity is locked before buying.

Once connected

  • For "scan token contracts for honeypot and rug risk", the likely first call is scan_token.
  • For "check whether liquidity is locked before buying", the likely first call is scan_token.
  • set_bots_claim_prefs change data without a sign-in: anyone with the address can call them.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 9, the first on 2026-10-27
  • INITE MCP score76 of 100answers 100 · does the job 100 · definitions 80 · context 99 · connects 100 · lowered by the warning signs below
  • What an agent can do with it2 of 2 use cases
  • Answered100% of days9 of 9 daily checks
  • Median first answer882 ms
  • Space in an agent's context≈ 3,151 tokensthe definitions of all its tools (22), which an agent carries on every turn
  • Tool definitionsB · 80 of 100
  • Typed results0 of 22 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 4 of 22
  • Not saying whether it only reads or can destroy: 22 of 22

What an agent can do with it

  • can do · scan token contracts for honeypot and rug risk
  • not sure · browse a screener of tokens on Robinhood Chain
  • can do · check whether liquidity is locked before buying

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: set_bots_claim_prefs

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers22 tools · read 2026-10-27
  • scan_token

    Composite on-chain safety verdict for any Robinhood-Chain (chain 4663) token: honeypot buy+sell simulation, LP-lock status, contract verification, deployer reputation, RWA-impostor detection. Returns PASS/CAUTION/DANGER.

  • get_scan_pricing

    Free quota, price per scan, the Robinhood Chain treasury address, live wei amounts, and the step-by-step pay-and-retry recipe for when scan_token returns error free_quota_exceeded.

  • search_token

    Find any Robinhood-Chain token by symbol, name, or address across the whole chain (not just the top pairs).

  • get_ohlcv

    On-chain OHLCV candles for a pool, for charting/backtesting.

  • get_stock_fundamentals

    Fundamentals for every US stock Robinhood has tokenized on Robinhood Chain (194 total, refreshed every 15min from public market data): price, market cap, trailing+forward P/E, EPS, price-to-book, dividend yield, 52-week high/low position…

  • get_swap_quote

    Read-only swap quote (no execution) for a token against the ScanHood swap contract — expected output for a given ETH-in (buy) or token-in (sell).

  • get_bridge_quote

    Read-only quote (no execution) for bridging native ETH/BNB between Robinhood Chain and Ethereum, Base, Arbitrum, or BNB Chain, via relay.link — the same route ScanHood's own Bridge tab uses. No ScanHood fee. Returns amountOut, an ETA in…

  • build_launch_tx

    Build (but do not sign or send) a launchToken transaction against ScanHood's live no-rug launchpad on Robinhood Chain — either Uniswap V3 (anti-snipe protection, supports an atomic initial buy) or V4 (Uniswap's newest, no anti-snipe…

  • get_watchlist

    Returns the token addresses a wallet has saved to its ScanHood watchlist.

  • save_watchlist

    Overwrites a wallet's saved token watchlist (up to 200 tokens). Requires a signature proving ownership of the address: sign the exact string in 'message' with that wallet's key (e.g. personal_sign / EIP-191) and pass it as 'signature'…

  • get_streak

    A wallet's consecutive-day ScanHood usage streak.

  • get_stockback_deck

    StockBack pays a share of real ScanHood trading-fee revenue as real tokenized stock, not points. Lists which real tokens are currently earnable and whether a reward auto-routes into a real covered-call yield vault.

  • get_stockback_vault

    Real Pending/Funded/Claimed StockBack state for one wallet. Pending is a promised USD value not yet backed by a purchase; Funded means a real on-chain stock purchase already confirmed and is waiting to be claimed; Claimed means it was…

  • get_scan_log

    Recent completed token safety scans across all of ScanHood (real activity, not a sample) — powers the "recent rugs caught" / "safe launches today" homepage modules. Optionally filter by verdict.

  • get_scan_rollup

    Daily counts of PASS/CAUTION/DANGER verdicts plus a sample of real DANGER catches per day, for up to 60 days back. Powers the weekly "State of the Chain" report.

  • apply_partner_key

    Get a free, higher-rate-limit (40r/s vs the 5r/s anonymous default) API key for a site that links back to scanhood.xyz. ScanHood fetches the site itself and checks for a real <a> to scanhood.xyz before issuing a key — self-reported claims…

  • get_partner_status

    Look up which site a partner key is registered to, when it was issued, and whether it has been upgraded to the paid tier.

  • get_paid_tier_info

    Treasury address and minimum payment to upgrade an existing partner key from the free tier (40r/s) to the paid tier (200r/s) via a Robinhood-Chain ETH payment.

  • upgrade_to_paid_tier

    After sending at least the minimum ETH (see get_paid_tier_info) to the treasury address on Robinhood Chain, submit the transaction hash here to upgrade an existing partner key to the paid tier (200r/s). Verifies the payment on-chain…

  • get_bots_stats

    Stats from ScanHood's own arbitrage and fee-claim bots.

  • get_bots_claim_prefs

    Per-token preferences for automatic trading-fee claiming.

  • set_bots_claim_prefs

    Enable or disable automatic fee claiming for a token. Requires a signature proving ownership of 'address': sign the exact string in 'message' with that wallet's key and pass it as 'signature'. Not usable without real wallet-signing…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "scanhood": {
      "type": "http",
      "url": "https://scanhood.xyz/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http scanhood https://scanhood.xyz/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://scanhood.xyz/mcp as a custom connector in the settings.

OpenAPI spec

10 paths, read 2026-10-27. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.