AroFlo MCP

AroFlo MCP

A production-ready MCP server that enables interaction with the AroFlo API to manage quotes, projects, and labor reporting. It features secure request signing and exposes API documentation as resources for enhanced context and tool surface.

Category
访问服务器

README

AroFlo MCP

Standalone, production-ready MCP server for AroFlo with first-class request signing and a clean tool surface.

Quick Start

Install (Local)

This repo ships an MCP server executable named aroflo-mcp (stdio transport by default).

Install the server on your machine (puts aroflo-mcp on your PATH via npm link):

make install

Install Into Codex (stdio)

  1. Create a local .env (not committed) with your credentials:
cp .env.example .env
# edit .env
  1. Register the server in Codex (stores env in ~/.codex/config.toml, not passed as tool args):
make codex-install
  1. Verify:
codex mcp get aroflo

Manual Codex Install (Alternative)

If you prefer doing it manually (same env variables, stored in Codex config):

codex mcp add aroflo \
  --env AROFLO_API_BASE_URL=https://api.aroflo.com/ \
  --env AROFLO_ACCEPT=text/json \
  --env AROFLO_SECRET_KEY=... \
  --env AROFLO_UENCODED=... \
  --env AROFLO_PENCODED=... \
  --env AROFLO_ORG_ENCODED=... \
  --env MCP_TRANSPORT=stdio \
  -- "$(command -v node)" "$(pwd)/dist/mcp/server.js"

Notes:

  • If Codex (desktop app) hangs starting the server, it is usually a PATH issue (common when Node is installed via nvm and the app is launched outside your shell).
  • Fix 1: Launch Codex from a terminal so it inherits your shell PATH (codex app).
  • Fix 2: Configure the MCP server to run via an absolute Node path (see docs/runbooks.md).

Development

Install dependencies:

npm install

Build and test:

npm run test
npm run build

Run server (stdio):

npm run dev

Run server (HTTP Streamable transport):

MCP_TRANSPORT=http npm run dev:http

MCP Inspector

To interactively test tools/list and tools/call via the official inspector UI:

make inspector

Project Layout

src/
  auth/
  aroflo/
  mcp/
  utils/
tests/
docs/

Environment

Required variables:

  • AROFLO_SECRET_KEY
  • AROFLO_UENCODED
  • AROFLO_PENCODED
  • AROFLO_ORG_ENCODED

Optional variables:

  • AROFLO_API_BASE_URL (default: https://api.aroflo.com/)
  • AROFLO_ACCEPT (default: text/json)
  • AROFLO_HOST_IP
  • AROFLO_TIMEOUT_MS (default: 65000)
  • AROFLO_MAX_RETRIES (default: 2)
  • LOG_LEVEL (default: info)

HTTP Transport

Set MCP_TRANSPORT=http to run an HTTP server (Streamable HTTP transport) at:

  • http://${MCP_HTTP_HOST}:${MCP_HTTP_PORT}${MCP_HTTP_PATH}

Using Extracted API Docs (docs/api)

This repo includes a local snapshot of the AroFlo API docs in docs/api/.

The MCP server exposes these markdown files as MCP resources so the client/LLM can look up valid WHERE fields, JOIN areas, etc:

  • aroflo://docs/api -> docs/api/README.md
  • aroflo://docs/api/<slug> -> docs/api/<slug>.md (example: aroflo://docs/api/quotes)

Example query: list Quotes with acceptance status "Awaiting Decision":

  • Tool: aroflo_get_quotes
  • Args:
{
  "where": "and|acceptancestatus|=|Awaiting Decision",
  "page": 1,
  "pageSize": 50
}

Example report: open projects with labour hours per task (recommended for progress reporting):

  • Tool: aroflo_report_open_projects_with_task_hours
  • Args (add optional filters like sinceDateRequested to keep outputs small):
{
  "sinceCreatedUtc": "2025-01-01",
  "sinceDateRequested": "2025-01-01",
  "hoursOnly": true,
  "includeTaskStatus": true,
  "mode": "data"
}

Docs

  • docs/aroflo-auth.md
  • docs/mcp-tools.md
  • docs/examples.md
  • docs/runbooks.md
  • docs/deployment.md
  • docs/api/*

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