Orisha Data MCP

Orisha Data MCP

Client-side MCP wrapper for Orisha Data's public x402 endpoints, providing free preview tools and paid market data access via x402 payments.

Category
访问服务器

README

Orisha Data MCP

Client-side MCP wrapper for the public Orisha Data x402 endpoints.

Orisha Data provides machine-readable market-data endpoints over HTTPS with x402 payment support. This wrapper lets an MCP-capable client inspect free previews and discovery documents before making paid x402 calls.

Public Endpoints

Base URL: https://orisha-data.com

Tool Public endpoint Price Notes
orisha_docs GET /docs Free Machine-readable service docs.
orisha_x402_discovery GET /.well-known/x402 Free x402 resource discovery.
orisha_signing_keys GET /.well-known/orisha-signing-key.json Free Public response-signing key set.
orisha_c1_preview GET /c1/preview/:pair Free Unsigned sample for the C1 price endpoint.
orisha_d1_preview GET /d1/preview Free Unsigned redacted D1 structure and freshness preview.
orisha_c1_price GET /c1/price/:pair $0.01 Paid x402 crypto/FX price response.
orisha_d1_levels GET /d1/levels $0.07 Paid x402 CME micro futures structural levels response.

D1 coverage window: Monday-Friday, 09:30-16:10 America/New_York. During active market windows, D1 may refuse overly stale data before payment instead of charging for unusable data.

Install

git clone https://github.com/OrishaAI/orisha-data-mcp.git
cd orisha-data-mcp
npm install

Run the free live smoke check:

npm run smoke

Run the MCP server over stdio:

npm run start

MCP Client Configuration

Example client configuration:

{
  "mcpServers": {
    "orisha-data": {
      "command": "node",
      "args": ["/absolute/path/to/orisha-data-mcp/src/server.mjs"],
      "env": {
        "ORISHA_DATA_BUYER_PRIVATE_KEY": "0xYOUR_BUYER_PRIVATE_KEY_PLACEHOLDER"
      }
    }
  }
}

The placeholder key above is intentionally not real. Use a buyer wallet only when you intend to call paid tools.

Free Evaluation Flow

An evaluating agent can try the service without payment:

  1. Call orisha_docs to read the public service documentation.
  2. Call orisha_x402_discovery to inspect the paid resource list.
  3. Call orisha_c1_preview with BTC-USD, ETH-USD, or SOL-USD.
  4. Call orisha_d1_preview to inspect D1 freshness and redacted structure.
  5. Call orisha_signing_keys to fetch the public key set used for paid response verification.

Equivalent direct HTTPS checks:

curl -s https://orisha-data.com/docs
curl -s https://orisha-data.com/.well-known/x402
curl -s https://orisha-data.com/c1/preview/BTC-USD
curl -s https://orisha-data.com/d1/preview
curl -s https://orisha-data.com/.well-known/orisha-signing-key.json

Paid Usage

Paid tools require a buyer wallet private key in the MCP client process:

ORISHA_DATA_BUYER_PRIVATE_KEY=0xYOUR_BUYER_PRIVATE_KEY_PLACEHOLDER npm run start

Available paid tools:

  • orisha_c1_price: calls the C1 paid price endpoint for a requested pair.
  • orisha_d1_levels: calls the D1 paid levels endpoint.

Responses from paid tools may include _signature. Verify those signatures using the key set at /.well-known/orisha-signing-key.json.

Response Signing

The public signing key set is available at:

https://orisha-data.com/.well-known/orisha-signing-key.json

The key set currently contains orisha-response-ed25519-v1. Treat the endpoint as a key set from day one so future rotations can add keys without changing client assumptions.

Safety

  • This package is client-side only.
  • Free tools do not require a buyer key.
  • Paid tools require a buyer key and may spend USDC through x402.
  • Do not put production buyer keys in examples, screenshots, issues, or logs.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选