aspro-mcp

aspro-mcp

Enables LLMs to interact with the Aspro.Cloud REST API through self-describing tools for discovering and calling modules, entities, and methods.

Category
访问服务器

README

aspro-mcp

npm version npm downloads install size types CI License: MIT Node

A Model Context Protocol server that exposes the Aspro.Cloud REST API to LLM clients (Claude Desktop, Claude Code, etc.). The server ships with the bundled OpenAPI spec, so the model can discover modules, entities and methods on its own and call them safely.

Features

  • Self-describing. The model browses the API via aspro_list_modules → aspro_list_entities → aspro_list_methods → aspro_describe, and only then aspro_calls — no need to memorize endpoints.
  • Substring search across module / entity / method / path / description / tags.
  • Form-urlencoded POSTs by default (Aspro's expected content type), with array and nested-object handling.
  • Path parameter substitution for /get/{id}, /update/{id}, /delete/{id} and friends.
  • Per-tenant config via ASPRO_COMPANY (subdomain) or full ASPRO_BASE_URL.

Install

git clone https://github.com/bssth/aspro-mcp.git
cd aspro-mcp
npm install
npm run build

Requires Node.js ≥ 18.

Configure

Copy the example env file and fill it in:

cp .env.example .env
ASPRO_COMPANY=your_company        # the {company} part of https://{company}.aspro.cloud
ASPRO_API_KEY=your_api_key_here   # passed as ?api_key=... on every request
# ASPRO_BASE_URL=...              # optional; overrides the URL built from ASPRO_COMPANY
# ASPRO_TIMEOUT_MS=30000          # optional; default 30s

Get an API key in your Aspro.Cloud account under Settings → Integrations → API.

Wire it up to a client

Claude Desktop / Claude Code

Add the server to your MCP config:

{
  "mcpServers": {
    "aspro": {
      "command": "node",
      "args": ["/absolute/path/to/aspro-mcp/dist/index.js"]
    }
  }
}

The server reads its .env from the project root regardless of the working directory the client launches it in.

Other MCP clients

Any client that speaks MCP over stdio can run node dist/index.js (or npm start).

Tools exposed

Tool What it does
aspro_list_modules List top-level modules (crm, fin, task, …) with entity / operation counts.
aspro_list_entities List entities inside a module and the methods available on each.
aspro_list_methods List operations (HTTP method + path + short description) for a module, optionally filtered by entity.
aspro_search Substring search across module / entity / method / path / description / tags.
aspro_describe Full schema for one operation: query / path params, body fields with types and descriptions.
aspro_call Execute the call. Returns { status, ok, url, data }.

The recommended flow is search/list_* → describe → call.

Develop

npm run dev      # tsc --watch
npm run build    # tsc
npm run smoke    # offline: exercises the spec indexer and URL builder

The smoke test does not hit the network — it checks that the bundled OpenAPI spec parses, that operations can be described, and that the URL builder produces well-formed URLs.

Project layout

src/
  index.ts    MCP server (tool registration + entry point)
  config.ts   .env loading and validation
  client.ts   HTTP client (URL building, form-urlencoded POSTs, timeouts)
  spec.ts    OpenAPI indexer (modules / entities / methods / search / describe)
  smoke.ts    offline smoke test
spec/
  openapi.json  bundled Aspro.Cloud OpenAPI spec

Security notes

  • The API key is read from the environment and appended to every request as ?api_key=.... Never commit .env.
  • The server has no allowlist — once configured, it can call any endpoint the spec describes (including destructive ones like /delete/{id}). Use a dedicated API key with the minimum necessary permissions.
  • Treat tool output as untrusted: Aspro entities (custom field values, descriptions, etc.) may contain user-supplied content.

Contributing

Issues and PRs welcome. Please run npm run build && npm run smoke before submitting.

License

MIT — see LICENSE.

aspro-mcp is an unofficial third-party connector and is not affiliated with Aspro.Cloud.

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
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
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
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
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
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
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