# tnt-house-risk-data-api [Health: Active]

**Category:** 💰 Finance & Fintech  
**Repository:** https://github.com/menantonio83-hue/tnt-house  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/tnt-house-risk-data-api

## Description
Solana token risk-scoring MCP server for AI trading agents with insider wallet cluster detection.

## Tools
Capabilities this server exposes over MCP:

- **check_token_risk** — Returns a 0-100 safety score, on-chain insider wallet clusters (wallets sharing a first funder), mint/freeze authority status, holder concentration, and live price/liquidity/volume for a single Solana token mint. Use before recommending or executing a trade on any Solana token. 5 free MCP calls/day, no signup. Then email key or x402.
- **check_token_risk_batch** — Same as check_token_risk but for up to 25 mints in one call — N mints charged as N calls, same per-call economics as check_token_risk, no bulk discount. All-or-nothing: if the batch can't be fully covered by remaining quota/credit, the whole batch is rejected rather than partially processed.
- **get_token_risk_history** — Returns hourly historical data points (safety_score, insider_cluster_count, holder_count, price, liquidity, volume) for a mint over the last N days (max 90). Free and unmetered — no quota, works with or without an API key — pure read from stored history, no live upstream call.

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "tnt-house-risk-data-api": {
    "url": "https://tnt-audit.com/api/mcp"
  }
}
```

## Documentation

## What tnt-house-risk-data-api does

tnt-house-risk-data-api provides MCP access to the RiskDataApi engine for Solana token analysis. Its results combine token safety indicators with market information, including price, liquidity, and volume. The service also identifies wallet groups that share a first funder, which can reveal relationships hidden when holders are viewed as separate addresses.

The main use cases are token screening and risk-aware analysis by AI agents. An agent can inspect one mint, compare a group of tokens, or request a time series showing how risk and market values changed over time.

## How it works

The remote MCP endpoint is available at `https://tnt-audit.com/api/mcp` and uses Streamable HTTP transport. MCP-compatible clients connect to that URL and invoke the registered tools. The repository identifies the MCP implementation as TypeScript code using the official Model Context Protocol SDK.

The underlying application uses Helius for Solana RPC data, RugCheck for risk information, and DexScreener for market data. The listing does not document a local MCP process or local data store that clients must run to make requests.

## Setup and configuration

A client can connect without an API key for the first five MCP calls per day.

```json
{
  "mcpServers": {
    "tnt-risk-data-api": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://tnt-audit.com/api/mcp"]
    }
  }
}
```

After the unauthenticated allowance, requests can use an API key obtained from the Risk-Data API page with an `Authorization: Bearer <api_key>` header. The documented service also offers x402 payment at $0.02 per call and a $45 subscription for 5,000 calls.

## Tools and capabilities

- `check_token_risk` analyzes one Solana token mint. Its output includes a safety score, insider wallet cluster detection, mint and freeze authority status, holder concentration, and live price, liquidity, and volume.
- `check_token_risk_batch` applies the same analysis to up to 25 token mints in one request.
- `get_token_risk_history` returns hourly historical risk and price data for a mint over a period of up to 90 days.

## Limitations and notes

The free, no-signup allowance is limited to five MCP calls per day. Higher usage requires an API key, paid access, or the documented x402 option.

The repository also includes a REST preview, but that is separate from the MCP interface. For MCP calls, clients should use the Streamable HTTP endpoint or the documented `mcp-remote` configuration. Local development instructions cover installing the project with npm and running its development server, while deployment is described as Vercel-ready.

_Full upstream README: https://allmcps.com/mcp/tnt-house-risk-data-api/readme_