Skip to content
Skinwinking logo

Skinwinking MCP server

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

read 2026-10-20

← Back to Skinwinking

Whose server it is
  • Registry namecom.skinwinking/agent-tollgateverified in the MCP registry

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

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools3
  • Server calls itselfagent-tollgate-engine
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 51 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check order book imbalance for a trading pair; screen token mints for freeze and mint authority risk.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "check order book imbalance for a trading pair", the likely first call is orderbook_imbalance.
  • For "screen token mints for freeze and mint authority risk", the likely first call is token_audit.
  • Parameters are untyped or undescribed in 2 of 3 tools: check arguments before calling.

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: 2, the first on 2026-10-20
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer120 ms
  • Space in an agent's context≈ 742 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsC · 72 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 3
  • Not saying whether it only reads or can destroy: 3 of 3

What an agent can do with it

  • can do · check order book imbalance for a trading pair
  • can do · screen token mints for freeze and mint authority risk
  • not sure · get swap routes and unsigned transactions across chains

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

None of the five warning signs in these definitions.

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 offers3 tools · read 2026-10-20
  • orderbook_imbalance

    Aggregates spot order book depth and returns bid/ask notional within 10/25/50/100 bps of mid, signed imbalance in [-1,1], largest liquidity walls and a directional signal. First 3 calls per day free, then 0.02 USDC per call via x402.

  • token_audit

    Rug-pull / honeypot check before you buy a token. Inspects mint and freeze authority, token-2022 extensions, proxy and ownership state, privileged functions and top holder concentration. Returns a 0-100 risk score with itemised flags…

  • swap_quote_and_build

    Free to call. Returns the best route and an unsigned transaction, and for Solana swaps a rug-pull risk check of the output token (mint/freeze authority, token-2022 traps, holder concentration) so agents do not buy honeypots. Same-chain…

How to connect

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

{
  "mcpServers": {
    "agent-tollgate": {
      "type": "http",
      "url": "https://skinwinking.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http skinwinking https://skinwinking.com/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

3 paths, read 2026-10-20. 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.