aspro-mcp
Enables LLMs to interact with the Aspro.Cloud REST API through self-describing tools for discovering and calling modules, entities, and methods.
README
aspro-mcp
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 thenaspro_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 fullASPRO_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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。