QMSCloud Reporting MCP Server
Enables querying pre-built Metabase cards for QMSCloud reporting, allowing retrieval of ticket summaries and other reports via natural language through AnythingLLM.
README
QMSCloud Reporting MCP Server — Node.js (Metabase)
Queries pre-built Metabase cards for QMSCloud and exposes them to AnythingLLM:
AnythingLLM (host) -> Ollama / Qwen -> this MCP server -> Metabase card JSON
Sibling of ../mcpreport (which talks to the QMS700i servlet). The difference:
this server has no login flow — Metabase authenticates with a static
x-api-key header, and each report is a saved Metabase card queried via
POST /api/card/<id>/query/json.
Tools
get_report(report, start_date?, end_date?)— fetch and return card rows.workspace_slugis injected by AnythingLLM (do not pass it manually).list_reports()— list available report keys.
Currently available reports: ticket_summary (card 40). Appointment, rating,
etc. will be added to the CARDS catalog in metabase-core.js.
How it works
- AnythingLLM injects
workspace_slugon every call. - The slug maps to a tenant
{ company_id, branch_id? }viaWORKSPACE_MAP.demo→company_id = 4f1589c0-5f9e-4f52-aee2-2b864204c14c(no branch_id).- Unknown slug → returns
invalid workspace slug.
- The model supplies
start_date/end_datefrom the user's intent. - The server POSTs the Metabase
parametersarray (start_date, end_date, company_id, and branch_id when present) to the card and returns the rows.
1. Install
Requires Node.js 18+ (built-in fetch).
cd /Users/koo/Desktop/Claude/Projects/QMS/metabase-mcpreport
npm install
2. Quick local test (no AnythingLLM)
The API key is not hardcoded — export it first:
export METABASE_API_KEY='mb_...your key...'
node test-ticket-summary.js # demo, month-to-date
node test-ticket-summary.js demo 2026-06-11 2026-06-30
3. Register in AnythingLLM
Add to anythingllm_mcp_servers.json (absolute paths):
{
"mcpServers": {
"qmscloud-report": {
"command": "node",
"args": ["/Users/koo/Desktop/Claude/Projects/QMS/metabase-mcpreport/server.js"],
"env": {
"METABASE_BASE_URL": "http://54.251.164.99:7777",
"METABASE_API_KEY": "mb_...PASTE_KEY..."
}
}
}
}
Windows note (same gotcha as ../mcpreport): if C:\Program Files\nodejs\node.exe
fails with ENOENT, use the 8.3 short path C:\\PROGRA~1\\nodejs\\node.exe.
4. Set the workspace system prompt
Paste the contents of system_prompt.txt into the AnythingLLM workspace system
prompt. It tells the model when/how to call get_report. Tools only fire in
@agent mode.
METABASE_API_KEY is required and is not hardcoded (kept out of source
control). Set it in the env block above. METABASE_BASE_URL defaults to
http://54.251.164.99:7777 if omitted.
Configuration reference
WORKSPACE_MAP(metabase-core.js) — slug →{ company_id, branch_id? }.CARDS(metabase-core.js) — report key → Metabase card id + params.
Notes
- Tools fire only in AnythingLLM
@agentmode. - Treat the Metabase API key as a secret; keep this config out of git.
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。