NLB Singapore Library MCP Server
Enables searching the National Library Board Singapore catalogue by title, author, ISBN, or subject, and checking real-time availability of books across library branches.
README
nlb-mcp
Unofficial FastMCP server for NLB Singapore Library Catalogue (availability + title search), implemented in Python.
What’s inside
- Language: Python 3.11+
- Framework: FastMCP (Python), httpx (HTTP), pydantic-settings (env), tenacity (retry)
- Tools (MCP):
health_check– validate env + startup readiness.search_titles– keyword search over BRN/ISBN/Title/Author/Subject.search_titles_advanced– fielded search with pagination/sorting.availability_by_title– branch-level availability for a title/ISBN/BID.
Project layout
nlb_mcp/
config.py # env validation (API keys, base URL, timeout)
http_client.py # httpx helper with retry/timeout
nlb_client.py # thin NLB REST client wrappers
models.py # lightweight normalized response shapes
server.py # FastMCP server + tool registration (with basic logging)
help/
nlb-swagger.json # upstream API spec for reference
Setup
- Create a virtualenv and install deps:
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
- Environment:
NLB_API_KEY=your_api_key
NLB_APP_CODE=your_app_code
# optional
NLB_API_BASE=https://openweb.nlb.gov.sg/api/v2/Catalogue
REQUEST_TIMEOUT_MS=10000
- Run locally:
fastmcp run nlb_mcp/server.py:create_server
FastMCP Cloud entrypoint
- Preferred:
nlb_mcp/server.py:create_server - Direct object exports:
nlb_mcp/server.py:server(aliasesmcp,app) FastMCP Cloud can point atnlb_mcp/server.py:create_server; it will handle OAuth2 for users. This server only uses NLBX-Api-Key/X-App-Codefrom env.
Auth model
- Client/user auth is handled by FastMCP’s built-in OAuth2 provider; this server does not add another layer of user auth.
- NLB API authentication uses env-provided keys only; never accept them from user input or log them.
- For per-user quotas/auditing, rely on FastMCP identity context when available.
Notes / TODO
- If you want stricter schemas, consider pydantic models for tool inputs/outputs.
- Add caching/rate limits if upstream limits are tight; httpx + tenacity already retry transient errors.
- Logging uses stdlib
logging(logger namenlb_mcp) with secret redaction; extend as needed for metrics or structured logs.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.