The Utility MCP Server provides AI assistants with tools for time management, data analysis, and observability integration.
Time Management Tools
get_current_time: Retrieve the current time in any timezone (e.g., Asia/Shanghai, UTC, America/New_York), returned asYYYY-MM-DD HH:MM:SS timezoneget_timestamp: Get the current Unix timestamp in seconds (timezone-independent)format_timestamp: Convert a Unix timestamp to a human-readableYYYY-MM-DD HH:MM:SS timezonestring in a specified timezone
ChatBI Data Analysis Tools
schema_search: Search project schemas using vector recall and keyword retrieval (with stages: tokenization, embedding, vector search, keyword search, fusion)execute_sql: Execute read-only PostgreSQL queries and return JSON results (with SQL Guardrail validation)
Observability Integration
Automatically logs tool usage to Langfuse for end-to-end tracing with nested stage logging
Propagates tracing context (traceparent headers) from upstream services like ChatBI
Deployment & Configuration
Runs in local (stdio) or remote (Streamable HTTP/SSE) modes
Supports Docker/Docker Compose deployment
Compatible with Cursor, Claude Desktop, and ChatBI/LangChain4j clients
Health check endpoint at
/health; configurable via environment variables
Provides capabilities to execute read-only PostgreSQL queries and perform schema searches using vector recall and keyword retrieval.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Utility MCP ServerWhat is the current time in Tokyo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server - 通用功能服务器
一个基于 Model Context Protocol (MCP) 的通用功能服务器，为 AI 提供扩展能力。
支持 本地模式 (stdio) 与 远程模式 (Streamable HTTP / SSE) 双模式运行，并可将 ChatBI -> MCP -> Langfuse 的观测链路串起来。
✨ 功能
🕐 时间工具
工具 | 描述 |
| 获取指定时区的当前时间 |
| 获取当前 Unix 时间戳 |
| 将时间戳转换为可读格式 |
📊 ChatBI 数据分析工具
工具 | 描述 |
| 基于向量召回 + 关键词检索返回项目相关 Schema |
| 执行只读 PostgreSQL 查询并返回 JSON 结果 |
🔭 Langfuse 链路观测
schema_search会记录嵌套阶段：分词、Embedding、向量检索、关键词检索、融合裁剪。execute_sql会记录嵌套阶段：SQL Guardrail 校验、SQL 执行。当上游 ChatBI 通过
traceparent和x-chatbi-*头透传上下文时，MCP 工具观测会自动挂到同一条 Langfuse Trace 下。
🚀 快速开始
安装依赖
uv sync本地模式运行
uv run mcp-server远程模式运行（默认推荐）
uv run mcp-server --remote --transport streamable-http --port 8000启动后可访问：
MCP:
http://localhost:8000/mcpHealth:
http://localhost:8000/healthSSE 兼容端点:
http://localhost:8000/sse
SSE 兼容模式
uv run mcp-server --remote --transport sse --port 8000🔌 客户端集成
本地模式配置
适用于 Cursor / Claude Desktop：
{
"mcpServers": {
"utility-server": {
"command": "uv",
"args": ["--directory", "/path/to/mcp-server", "run", "mcp-server"]
}
}
}远程模式配置
ChatBI / LangChain4j
直接连接 Streamable HTTP 端点：
http://your-server:8000/mcp兼容 mcp-remote 的 SSE 客户端
{
"mcpServers": {
"utility-server": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://your-server:8000/sse"]
}
}
}🐳 Docker 部署
使用 Docker Compose（推荐）
docker compose up -d
docker compose logs -f
docker compose down手动 Docker 命令
docker build -t mcp-server .
docker run -d -p 8000:8000 --name mcp-server mcp-server
docker run -d -p 9000:9000 -e PORT=9000 --name mcp-server mcp-server🔐 Langfuse 配置
在 .env 中配置：
LANGFUSE_ENABLED=true
LANGFUSE_HOST=https://cloud.langfuse.com
LANGFUSE_PUBLIC_KEY=pk-lf-xxxx
LANGFUSE_SECRET_KEY=sk-lf-xxxx
LANGFUSE_ENVIRONMENT=production
MCP_SERVER_RELEASE=2026.03.09如果未配置 Langfuse 凭证，服务仍可正常提供 MCP 工具，只是不会上报 tracing 数据。
🧪 开发测试
uv run mcp dev src/mcp_server/server.py
uv run mcp-server --help📖 架构说明
ChatBI Java Service
|
| traceparent + x-chatbi-* headers
v
External MCP Server (/mcp)
|
|-- schema_search
| |-- tokenize
| |-- embedding
| |-- vector_search
| |-- keyword_search
| `-- fusion
|
`-- execute_sql
|-- validate
`-- query
All observations -> Langfuse📄 许可证
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.