Skip to main content
Glama

UML Search MCP Server

An MCP server for searching across the UMass Lowell web domain.

Usage

The MCP server can be used locally by either

  • Run as host process: uv run server.py

    • Accessible at localhost:8000/mcp

  • Run as a docker container with Prometheus: docker compose up

    • Accessible at 0.0.0.0:8000/mcp or localhost:8000/mcp locally

    • Prometheus accessible at localhost:9090

NOTE

If you're using the MCP Inspector tool for local development, uml-search-mcp uses the Streamable HTTP transport, not STDIO or server-sent events (SSE).

Related MCP server: web-mcp

☸ Kubernetes

For production deployments on kubernetes check the reference manifests in k8s.

🧩 Technologies

  • Docker

  • Docker Compose

  • MCP

  • Prometheus

🛠️ Tool Calls

Tool Calls

🔬 Metrics

This MCP server exposes a Proemtheus /metrics endpoint which can be scraped for metrics

The k8s/ directory also contains a ServiceMonitor manifest to point a Prometheus instance on k8s to the MCP server.

Application Metrics exposed:

  • uml_search_mcp_tool_calls_total: Total number of MCP tool executions for uml-search-mcp

  • uml_search_mcp_tool_execution_seconds: Time spent executing on MCP tool in seconds for uml-search-mcp

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides functionality to fetch and transform web content in various formats (HTML, JSON, plain text, and Markdown) through simple API calls.
    73,147 npm
    1
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables web search using DuckDuckGo and content retrieval from URLs, returning markdown with pagination support.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables web search via DuckDuckGo and content extraction from URLs using Readability.js.
    46 npm
    1
    Do What The F*ck You Want To Public
  • A
    license
    Not graded
    quality
    B
    maintenance
    Provides lightweight web crawling and scraping capabilities, enabling users to fetch pages as clean Markdown, recursively crawl domains, extract metadata, and perform search-and-crawl operations.
    2 npm
    MIT