uml-search-mcp
Allows searching across the UMass Lowell web domain.
Click on "Deploy 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., "@uml-search-mcpsearch for Dr. Smith in computer science department"
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.
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.pyAccessible at
localhost:8000/mcp
Run as a docker container with Prometheus:
docker compose upAccessible at
0.0.0.0:8000/mcporlocalhost:8000/mcplocallyPrometheus accessible at
localhost:9090
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

🔬 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-mcpuml_search_mcp_tool_execution_seconds: Time spent executing on MCP tool in seconds for uml-search-mcp
This server cannot be deployed
Maintenance
Related MCP Connectors
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract.
Link-preview metadata and clean page-to-Markdown for any public URL. No install.
Search Multilo's docs, fetch any public page as clean Markdown, and read the changelog.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides functionality to fetch and transform web content in various formats (HTML, JSON, plain text, and Markdown) through simple API calls.73,147 npm1MIT
- FlicenseNot gradedqualityCmaintenanceEnables web search using DuckDuckGo and content retrieval from URLs, returning markdown with pagination support.-
- AlicenseNot gradedqualityDmaintenanceEnables web search via DuckDuckGo and content extraction from URLs using Readability.js.46 npm1Do What The F*ck You Want To Public
- AlicenseNot gradedqualityBmaintenanceProvides 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 npmMIT