eth-library-mcp
This MCP server gives AI assistants direct, read-only access to ETH Library Zurich's 30M+ catalogue and archival collections through a standardised interface.
Search all resources (
eth_search_resources): full-text discovery across 30M+ books, maps, images, archival materials, etc., with fields (any,title,creator,sub), operators (contains,exact,begins_with), facets, pagination, language/resource-type/open-access filters.Fetch resource details (
eth_get_resource): full metadata for a specific item using its Alma MMS-ID, including availability.Search archives (
eth_search_archive): query specific collections — ETH University Archives, Max Frisch Archive, Thomas Mann Archive, Graphische Sammlung, and Bildarchiv/E-Pics.Search by resource type (
eth_search_by_type): filter by books, journals, articles, maps, images, archival materials, scores, databases, audios, videos.Curated education search (
eth_search_education): optimised for pedagogy, school history, and education topics (e.g. "Volksschule Zürich").Server overview (
eth_library_info): list all available resource types and archives at a glance.Resources & prompts: exposes
eth://resource-typesandeth://archives, plus built-inresearch-workflowandeducation-researchprompts.Dual transport: runs over stdio for Claude Desktop or Streamable HTTP/SSE for cloud/browser use.
Safety: read-only GET operations only, no personal data, requires a free ETH Library API key, no caching or writes.
Note: the schema still lists eth_search_persons, but the README states this tool was intentionally removed because the Persons API no longer exists on the gateway.
Enriches person records with linked data from Wikidata for enhanced person search results.
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., "@eth-library-mcp Search the Max Frisch archive for manuscripts."
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.
🇨🇭 Part of the Swiss Public Data MCP Portfolio
🏛️ eth-library-mcp
🌐 English | Deutsch
MCP server giving AI models direct access to 30M+ resources at ETH Library Zurich – books, maps, images and archival material.
Demo
Overview
eth-library-mcp connects AI assistants like Claude to the largest natural-science library in Switzerland. It exposes full-text search, archive-level queries and resource-type filtering via the ETH Library's Discovery API – all through a single, standardised MCP interface.
6 Tools · 1 API · 2 Resources · 2 Prompts
MCP Protocol Version: 2026-07-28 (via mcp[cli]>=2.0.0,<3).
BUG-02 is resolved — by removing the tool.
eth_search_personswas documented as "currently non-functional, correct URL to be verified". It has now been verified, and there is no correct URL: the Persons API is gone from the gateway, not merely locked. The gateway routes before it checks the API key, so an existing route answers401and a missing one answers404—/discovery/v1/resourcesgives 401, every/persons/v1/*path gives 404, and so does a deliberately invented Discovery path used as a control. Offering a capability that cannot exist is the same mistake as returning an empty result, only louder. The measurement is recorded and dated intests/fixtures/api_routes.json.
Anchor demo query: "Find historical documents about Zurich school history in the ETH Library archives."
Related MCP server: swiss-cultural-heritage-mcp
Features
🔍 Full-text search over 30M+ resources with fields, operators, and facets
📖 Resource details – full metadata via MMS-ID
🗂️ Archive search – ETH University Archives, Max Frisch, Thomas Mann, Graphische Sammlung, Bildarchiv
🏷️ Resource type filter – books, maps, images, archival material and more
🎓 Education search – curated workflow optimised for pedagogy and school history
📋 Server overview – all resource types and archives at a glance
🗣️ Built-in prompts – structured research and education-research workflows
☁️ Dual transport – stdio for Claude Desktop, Streamable HTTP/SSE for cloud deployment
Prerequisites
Python 3.11+
A free API key from developer.library.ethz.ch
Installation
# Clone the repository
git clone https://github.com/malkreide/eth-library-mcp.git
cd eth-library-mcp
# Install
pip install -e .
# Or with uv (recommended)
uv pip install -e .Quickstart
# Set the API key
export ETH_LIBRARY_API_KEY=your_key_here # macOS / Linux
# $env:ETH_LIBRARY_API_KEY = "your_key_here" # Windows (PowerShell)
# Start the server (stdio mode for Claude Desktop)
python -m eth_library_mcp.serverWithout an API key the server returns a helpful error message with the registration link – no crashes.
Try it immediately in Claude Desktop:
"Find books about Swiss education history in the ETH Library." "Search the Max Frisch archive for manuscripts about Zurich."
→ More use cases by audience →
Configuration
Environment Variables
Variable | Description | Required |
| API key for the Discovery API | ✅ |
| Log level ( | — |
| Comma-separated CORS allow-origins for | — |
| Comma-separated hostnames this server is reachable under. Required for a non-loopback bind ( | — |
Claude Desktop Configuration
{
"mcpServers": {
"eth-library": {
"command": "python",
"args": ["-m", "eth_library_mcp.server"],
"env": {
"ETH_LIBRARY_API_KEY": "your_key_here"
}
}
}
}Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Cloud Deployment (SSE for browser access)
For use via claude.ai in the browser (e.g. on managed workstations without local software):
python -m eth_library_mcp.server --http --port 8000The HTTP transport binds to 127.0.0.1 by default. To expose it on another
interface, pass --host explicitly:
# Only behind a reverse-proxy / firewall that terminates TLS and enforces auth.
python -m eth_library_mcp.server --http --host 0.0.0.0 --port 8000⚠️ Do not bind to
0.0.0.0without a reverse proxy. The server has no built-in auth, rate-limiting or TLS — any LAN neighbour could call your tools.
💡 "stdio for the developer laptop, HTTP for the browser — behind a proxy."
Available Tools
Discovery API (api.library.ethz.ch)
Tool | Description |
| Full-text search over 30M+ resources with fields, operators, facets |
| Full metadata for a specific resource via MMS-ID |
| Search within a specific archive (University Archives, Max Frisch, Thomas Mann, etc.) |
| Filter by resource type (books, maps, images, archival material, etc.) |
| Curated search for education topics (pedagogy, school history, etc.) |
Utilities
Tool | Description |
| Server overview: all types and archives at a glance |
Resources & Prompts
Item | Type | Description |
| Resource | All available resource types |
| Resource | All available archives and collections |
| Prompt | Structured research workflow |
| Prompt | Education topics workflow (Schulamt-optimised) |
Query Syntax
The Discovery API uses structured queries:
field,operator,valueField | Meaning |
| All fields (recommended for starters) |
| Title only |
| Author / creator |
| Subject headings / topics |
Operator | Meaning |
| Term is present |
| Exact match |
| Starts with |
Examples:
any,contains,Volksschule Zürich
title,contains,Pädagogik
creator,exact,Einstein Albert
sub,contains,Bildungsforschung
title,contains,Schule;sub,contains,GeschichteAvailable Archives
Identifier | Description |
| Institutional memory of ETH Zurich |
| Estate of Swiss author Max Frisch |
| Letters and documents of Thomas Mann |
| Prints, drawings, graphic works |
| Science/technology history, Swissair (E-Pics) |
Example Use Cases
Query | Tool |
"Find books about Zurich school history" |
|
"What's in the Max Frisch archive?" |
|
"Find historical maps of Switzerland" |
|
"Get full metadata for resource ID 991170525863705501" |
|
"Which archives does the ETH Library hold?" |
|
Project Structure
eth-library-mcp/
├── src/
│ └── eth_library_mcp/
│ ├── __init__.py # Package init, version
│ └── server.py # FastMCP server, all tools
├── tests/
│ └── test_server.py # Unit tests
├── CHANGELOG.md
├── CONTRIBUTING.md # Contribution guide (English)
├── CONTRIBUTING.de.md # Contribution guide (German)
├── SECURITY.md # Security posture (English)
├── SECURITY.de.md # Security posture (German)
├── LICENSE
├── README.md # This file (English)
├── README.de.md # German version
├── claude_desktop_config.json # Example Claude Desktop configuration
└── pyproject.toml # Build configurationMCP Protocol Version
This server speaks two protocol eras over the same endpoint. The client's first request on a connection decides which one applies; a later claim from the other era is refused.
Era | Revision | Who reaches it |
|
| What today's clients speak. The server answers with the revision asked for, or with the |
Per-request envelope |
| A request carrying the |
Both revisions are pinned in
tests/test_protocol_version.py and asserted
against the installed SDK, so a Dependabot bump of mcp cannot move either one
silently. The handshake ceiling is measured against a live initialize through
the assembled ASGI stack, not read off a constant name.
Note that the SDK's LATEST_PROTOCOL_VERSION is an alias for the modern
era, not for the handshake era — pinning against it alone would leave the era
that current clients actually negotiate free to drift.
Update policy. When the gate fails, do not edit the constant blindly: read
the spec changelog between the two revisions, verify the server still behaves,
then move the constant, this section, README.de.md and
CHANGELOG.md together.
Server identity (serverInfo)
2026-07-28 stamps the server's Implementation block into every modern
result under _meta.io.modelcontextprotocol/serverInfo (spec #3002) — earlier
revisions carried it only in the initialize result. What used to be a
one-time field is now repeated on every call, and version is required.
The SDK fills none of it: "An unversioned server reports an empty version;
the SDK never substitutes its own." Measured against the assembled ASGI stack,
this server used to answer "version": "" in both eras while server.json
told the registry 0.3.4. It now declares:
Field | Value | Source |
|
| the programmatic identifier — the same string as the distribution name in |
| ETH-Bibliothek Zürich |
|
| the installed distribution's version |
|
| the distribution summary |
|
| the |
|
icons stays unset: this repository ships none, and an invented path would
assert a file that does not exist.
Measured, not read back, in
tests/test_server_identity.py: the
assertions drive a real modern POST through build_http_app(). A look at
mcp.version would stay green even if the constructor argument were lost or
the SDK stopped stamping at all.
Testing
# Unit tests (no API key required)
PYTHONPATH=src pytest tests/ -m "not live"
# Integration tests (API key required)
# Live checks against the gateway — these need NO API key
PYTHONPATH=src pytest tests/ -m "live"
# Re-record the route census (writes tests/fixtures/PROVENANCE.md)
python scripts/record_fixtures.pyUntil 2026-08-08 this repository had no live tests at all — pytest -m live
collected zero. Nothing in it had ever been held against the source.
The Discovery payloads still cannot be recorded: the API requires a key, and
tests/fixtures/PROVENANCE.md lists them explicitly as NOT RECORDED rather
than giving them a date they never had. What is recordable is the contract the
source gives up without a key — which routes the gateway serves — and that is
exactly what the finding hangs on. The two control_* entries are part of the
measurement, not decoration: without them the recording only proves that someone
got a 404; with them it proves what the gateway distinguishes.
The two live tests need no key and say something anyway: they report if the Persons API comes back (then the tool should return) or if Discovery loses its route (then five tools are affected).
Safety & Limits
Read-only: All tools perform HTTP GET requests only — no data is written, modified, or deleted.
No personal data: The APIs return bibliographic metadata (titles, authors, subjects, identifiers). No personally identifiable information (PII) is processed or stored by this server.
Authentication: A free API key from developer.library.ethz.ch is required. The key is read from the
ETH_LIBRARY_API_KEYenvironment variable and never logged or transmitted to third parties.Rate limits: The ETH Library API enforces rate limits per API key. The server enforces a 30-second timeout per request. Use
limitandoffsetparameters conservatively.Data freshness: Results reflect the ETH Library catalogue at query time. No caching is performed by this server.
Terms of service: Bibliographic metadata is published as Public Domain — free for all uses. API access is subject to the ETH Library Developer Portal terms.
No guarantees: This is a community project, not affiliated with the ETH Library or ETH Zurich. Availability depends on upstream APIs.
Contributing
Contributions are welcome! See CONTRIBUTING.md (Deutsch) for guidelines.
Security
Read-only, no PII, a single upstream API key, and a fixed egress allow-list of ETH Library endpoints. See SECURITY.md (Deutsch) for the full security posture and accepted-risk decisions.
Changelog
See CHANGELOG.md
License
Server code: MIT License — see LICENSE
Bibliographic metadata: Public Domain (no restrictions)
API documentation: developer.library.ethz.ch
Author
Hayal Oezkan · github.com/malkreide
Powered by Model Context Protocol • 1 API • 6 Tools • 2 Resources • 2 Prompts
Installation
Run via uv's uvx — no clone or manual install needed. Add to your MCP client config (mcpServers for Claude Desktop, Cursor and Windsurf; use a top-level servers key for VS Code in .vscode/mcp.json):
{
"mcpServers": {
"eth-library-mcp": {
"command": "uvx",
"args": [
"eth-library-mcp"
]
}
}
}Available Tools
6 toolseth_get_resourceARead-onlyIdempotent
Ruft eine einzelne Ressource der ETH-Bibliothek anhand ihrer MMS-ID ab.
FID-003: Kennt die Quelle die MMS-ID nicht, kommt ein leeres Ergebnis mit
hint — keine geratenen Angaben zu einem Datensatz, der nicht geliefert
wurde. Ein Fehlschlag (401, 404, Zeitüberschreitung) kommt dagegen als
isError und ist keine Aussage über den Bestand.
Inputs: params (required).
eth_library_infoBRead-onlyIdempotent
Gibt eine Übersicht über den ETH Library MCP Server zurück.
Inputs: no named parameters. Returns: result
eth_search_archiveARead-onlyIdempotent
Durchsucht ein spezifisches Archiv oder eine Sammlung der ETH-Bibliothek.
FID-003: Ein leeres Ergebnis nennt im Feld hint den nächsten Versuch —
das Archiv ist ein Filter, und der Bestand ausserhalb davon ist damit
nicht geprüft. Keine geratene Angabe an die Stelle eines fehlenden
Treffers setzen.
Inputs: params (required).
eth_search_by_typeBRead-onlyIdempotent
Sucht Ressourcen eines bestimmten Typs (Karten, Bilder, Archive, etc.).
FID-003: Ein leeres Ergebnis nennt im Feld hint den nächsten Versuch —
der Typfilter ist eine Einschränkung, und was ausserhalb davon liegt, ist
damit nicht geprüft. Keine geratene Angabe an die Stelle eines fehlenden
Treffers setzen.
Inputs: params (required).
eth_search_educationARead-onlyIdempotent
Kuratierte Suche nach bildungsrelevanten Ressourcen in der ETH-Bibliothek.
FID-003: Ein leeres Ergebnis nennt im Feld hint den nächsten Versuch.
Eine geratene Literaturangabe darf nie an die Stelle eines fehlenden
Treffers treten — auch dann nicht, wenn der Titel plausibel klingt.
Inputs: params (required).
eth_search_resourcesARead-onlyIdempotent
Durchsucht den Katalog der ETH-Bibliothek mit über 30 Millionen Ressourcen.
Nutzt die Discovery API (api.library.ethz.ch/discovery/v1/resources). Unterstützt Freitextsuche, Feldsuche, Facetten-Filter und Pagination.
FID-003: Ein leeres Ergebnis ist eine Aussage über den Bestand, keine
Einladung zum Raten. Kommt nichts zurück, steht der nächste Suchversuch
im Feld hint der strukturierten Antwort; er gehört ausgeführt, bevor
Abwesenheit gemeldet wird. Eine geratene Angabe darf nie an die Stelle
eines fehlenden Treffers treten.
Inputs: params (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
The tools are mostly distinct: general catalog search, MMS-ID retrieval, archive-scoped search, type-scoped search, curated education search, and server info. Some overlap exists because search_archive and search_by_type are essentially filtered variants of eth_search_resources, but the dedicated purposes are described clearly enough to avoid serious misselection.
All tools share the eth_ prefix and the search tools follow a consistent eth_search_* pattern. eth_get_resource uses verb_noun consistently, but eth_library_info deviates from the verb-led convention, making the naming mostly predictable rather than fully uniform.
Six tools is a well-scoped size for a library search server. Each tool covers a meaningful discovery or retrieval function, and there is no sense of padding or missing essential surface.
The server covers the core read-only domain well: general search with facets and pagination, single-record retrieval by MMS-ID, archive and type-specific search, and a curated education search. Minor gaps like listing available archives or exposing holding/availability details are absent, but agents can work around them using the general search tool.
Maintenance
Related MCP Connectors
Knowledge commons for AI agents: cited, licensed, queryable claims over MCP.
Open network for AI agents to find, exchange and reuse structured knowledge via MCP and JSON.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP server that provides standardized access to biomedical knowledge bases and resources, enabling AI systems to retrieve verified information from sources like bioRxiv, EuropePMC, and various protein/gene databases.5233Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI-native access to Swiss cultural heritage data from SIK-ISEA (artists), Nationalmuseum (collections), and Nationalbibliothek (bibliography) via MCP tools, without authentication.1129 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceA unified MCP server for biomedical research that connects AI systems to resources like Ensembl, EuropePMC, STRING, and more, enabling retrieval of verified domain-specific information.Apache 2.0
- AlicenseBqualityBmaintenanceAn MCP server providing AI-powered access to Open Data from the City of Zurich, enabling queries to 900+ datasets, real-time environmental and mobility data, geodata, parliamentary proceedings, and more.2666 PyPI9MIT