sru-mcp

An MCP server that searches library catalogs worldwide using the SRU (Search/Retrieve via URL) protocol. No API keys required — SRU is an open standard supported by national libraries, university catalogs, and consortia.

Features

• 5 tools for LLM-driven bibliographic search

• 7 pre-configured servers including Library of Congress, BnF, DNB, and more

• Parses MARCXML and Dublin Core record formats

• Supports any SRU-compliant server — pass a URL or use a built-in server ID

• Raw CQL queries or high-level field-based search (title, author, ISBN, subject, etc.)

Related MCP server: Books & Film MCP Server

Quick Start

Install

pip install mcp[cli] httpx xmltodict

Run

python server.py

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "sru": {
      "command": "python",
      "args": ["/path/to/sru-mcp/server.py"]
    }
  }
}

Tools

Example Usage

Search the Library of Congress for books by Melville:

sru_search_books(server="loc", author="Melville", title="Moby Dick")

Search the French national library with a raw CQL query:

sru_search(server="bnf", cql_query='dc.title = "Les Misérables"')

Pre-configured Servers

To add a server, edit servers.json.

Development

# Install dev dependencies
pip install pytest pytest-asyncio respx

# Run tests
python3 -m pytest test_sru.py test_server.py -v

# Test with MCP Inspector
npx @modelcontextprotocol/inspector python server.py

Project Structure

server.py       FastMCP server — tool definitions
sru.py          SRU protocol client — HTTP, parsing, formatting
servers.json    Server registry
test_sru.py     Tests for sru.py (92 tests total)
test_server.py  Tests for server.py

License

MIT