zbmath-mcp
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., "@zbmath-mcp search for recent papers on quantum topology"
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.
zbmath-mcp
MCP server for zbMath Open — the world's most comprehensive reviewed database of mathematical literature.
This server exposes the zbMath Open REST API as Model Context Protocol (MCP) tools, enabling AI assistants such as Claude to search and retrieve mathematical publications, author profiles, and software entries directly.
Tools
Tool | Description |
| Free-text search across 4.5 M+ zbMath documents |
| Fetch full metadata for a document by its zbMath ID |
| Field-filtered search (author, title, MSC code, year range, journal) |
| Fetch an author profile by zbMath author ID |
| Fetch a software / swMath entry by its numeric ID |
Related MCP server: arxiv-reader-mcp
Requirements
Python 3.11+
uv(recommended) orpip
Installation
Using uv (recommended)
Installs a global zbmath-mcp command:
uv tool install git+https://github.com/iwaokimura/zbmath-mcp.gitUsing pip
pip install git+https://github.com/iwaokimura/zbmath-mcp.gitFrom source
git clone https://github.com/iwaokimura/zbmath-mcp.git
cd zbmath-mcp
uv sync(With plain pip instead of uv, run pip install -e . in place of uv sync.)
Usage
Running the server
If you installed it as a tool (uv) or with pip:
zbmath-mcpFrom a source checkout:
uv run zbmath-mcpThe server communicates over stdio using the MCP protocol, so running it in a plain terminal just waits for a client to connect — that is expected. Normally an MCP client (see below) launches it for you.
Connecting with Claude Desktop
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"zbmath": {
"command": "zbmath-mcp"
}
}
}Or, to run from a source checkout without installing (replace the path with your clone location):
{
"mcpServers": {
"zbmath": {
"command": "uv",
"args": ["--directory", "/path/to/zbmath-mcp", "run", "zbmath-mcp"]
}
}
}Connecting with Claude Code (CLI)
If installed as a command:
claude mcp add zbmath -- zbmath-mcpOr from a source checkout (replace the path with your clone location):
claude mcp add zbmath -- uv --directory /path/to/zbmath-mcp run zbmath-mcpExample interactions
Once connected, you can ask an AI assistant:
"Search zbMath for papers on the Langlands program from the last 5 years."
"Get the zbMath document with ID 7192477."
"Find all papers by Euler in zbMath."
"Search for papers in MSC class 11 (Number Theory) published between 2000 and 2010."
"Look up the software entry for Macaulay2 on swMath."
Development
git clone https://github.com/iwaokimura/zbmath-mcp.git
cd zbmath-mcp
uv sync # installs runtime + dev dependencies
uv run pytest # run the test suiteLicense
MIT — see LICENSE.
Available Tools
5 toolsget_authorA
Retrieve profile information for a zbMath author by their profile ID.
Args: author_id: The zbMath author profile identifier string, e.g. "euler.leonhard" or "gauss.carl-friedrich".
Returns: JSON string with the author's profile data including name variants, affiliated institutions, and publication count.
Inputs: author_id (required). Returns: result
get_documentA
Retrieve full metadata for a single zbMath document by its numeric ID.
Args: zbmath_id: The numeric zbMath document identifier (e.g. 7192477 for Zbl 7192477).
Returns: JSON string with complete document metadata including title, authors, abstract, MSC classification, journal, DOI, review, and links.
Inputs: zbmath_id (required). Returns: result
get_softwareA
Retrieve metadata for a zbMath / swMath software entry by its numeric ID.
Args: software_id: The numeric swMath software identifier.
Returns: JSON string with software metadata including name, description, programming language, keywords, and references.
Inputs: software_id (required). Returns: result
search_documentsA
Search zbMath Open for mathematical documents using a free-text query.
Args: query: Free-text search string, e.g. "Riemann hypothesis" or "spectral theory elliptic operators". results_per_page: Number of results to return (1–100, default 10). page: Zero-based page index for pagination (default 0).
Returns: JSON string containing total result count and a list of matching documents, each with id, title, authors, year, journal, MSC codes, a short review excerpt, and a zbMath URL.
Inputs: query (required), page, results_per_page. Returns: result
structured_searchA
Search zbMath documents using structured field filters.
Use this instead of search_documents when you want to restrict results to specific fields such as author name, MSC subject class, or year range.
Args: author: Author (contributor) name, e.g. "Euler" or "Riemann, B.". title: Words or phrases to match in the document title. msc_code: MSC 2020 classification code, e.g. "11" for Number Theory or "35J15" for a specific code. year_from: Earliest publication year (inclusive). year_to: Latest publication year (inclusive). journal: Journal / bibliographic source name fragment. results_per_page: Number of results (1–100, default 10). page: Zero-based page index for pagination (default 0).
Returns: JSON string with total result count and matching documents.
Inputs: page, title, author, journal, +4 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct purpose: author profile, document metadata, software metadata, free-text document search, and structured document search. Even the two search tools are clearly differentiated by their query style (free-text vs. field-specific filters).
All tools follow a consistent verb_noun pattern in lowercase snake_case (get_author, get_document, get_software, search_documents, structured_search). The convention is uniform and predictable.
With 5 tools, the server is well-scoped for a mathematical reference database. It covers retrieval of three core entity types (author, document, software) and two complementary search modalities (free-text and structured).
The tool surface covers essential retrieval and search operations, but lacks dedicated search endpoints for authors or software. While structured_search can filter documents by author, it cannot return author profiles or software entries directly, which is a minor gap.
Maintenance
Related MCP Connectors
Academic research MCP server for paper search, citation checks, graphs, and deep research.
arXiv MCP — preprint server search (free, no auth)
Peer-reviewed scientific paper & arXiv preprint search MCP with citations, abstracts & PDF links.
The only MCP server for Arabic academic research — search, read & cite Arabic + English papers.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for searching Ex Libris Primo library catalogues and subscribed databases, enabling search, record retrieval, autocomplete, citation generation, and export to BibTeX, RIS, or CSV.59MIT
- AlicenseAqualityCmaintenanceMCP server for searching and retrieving arXiv papers with full-text PDF extraction.52MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for academic research using the OpenAlex API, enabling article search, details retrieval, and author profile lookup.-
- AlicenseAqualityBmaintenanceAn MCP server for academic literature research that integrates Scopus, CrossRef, OpenAlex, and Unpaywall to search documents, get abstracts, author profiles, citing papers, and open-access PDF links.9MIT