Skip to main content

English | 中文文档

mcp-zenodo — Zenodo MCP Server

mcp-zenodo is a Zenodo MCP server: it connects large language models to Zenodo, the CERN-hosted open-access research repository, through the Model Context Protocol (MCP). It lets an LLM search Zenodo records, read metadata, retrieve citations, and list or download files as callable tools. It is built for developers and researchers who want AI assistants to work with open research datasets, software, and publications. Use it when you want tools like Claude Desktop, Cursor IDE, or a LangChain/LangGraph agent to ground answers in real Zenodo records with DOIs. Do not use it if you need to deposit or publish to Zenodo, since this project is read/retrieval oriented and does not implement upload workflows. Compared with calling the Zenodo REST API directly, mcp-zenodo packages that access as MCP tools so any MCP-compatible client can use Zenodo without writing custom integration code.

One-line value prop: an MCP server for Zenodo that turns open-access research data into LLM-callable tools.

一句话介绍:把 Zenodo 开放获取研究数据变成 LLM 可调用的 MCP 工具。

Written in Python. Licensed under Apache-2.0.


中文简介

mcp-zenodo 是一个 Zenodo MCP 服务器,通过模型上下文协议(MCP)将大语言模型连接到 Zenodo(CERN 托管的开放获取研究仓库)。它让 LLM 能够以可调用工具的方式搜索记录、读取元数据、获取引用、列举或下载文件。支持 Claude Desktop、Cursor IDE、Qoder 等 MCP 客户端,以及 LangChain/LangGraph 等 LLM 框架。

# 一键启动(无需克隆)
uvx mcp-zenodo

# 或安装
pip install mcp-zenodo

完整中文文档请见 README.zh.md。


What it does

mcp-zenodo exposes Zenodo's repository of research outputs to LLMs through MCP tools:

  • Search and retrieve records — find Zenodo records by query.
  • Get citations — retrieve citations in formats such as BibTeX and APA.
  • Detect data types — classify a record as dataset, software, or article.
  • Access metadata — get detailed metadata for a record.
  • List and download files — browse and download files attached to records.

Available tools

Tool Description
search_records Search for records in Zenodo
get_metadata Retrieve detailed metadata of a Zenodo record
get_citation Return a BibTeX or APA citation of a Zenodo record
detect_data_type Determine if a record is a dataset, software, or article
compare_records Compare metadata of multiple Zenodo records
list_files List available files in a Zenodo record
download_file Download a specific file from a record
generate_embed_link Create a direct embeddable link for a record (PDF, dataset)
extract_keywords Extract top keywords from a record's abstract or text
get_related_records Find records related to a given Zenodo record
summarize_record Generate a summary from a record's metadata

Package structure

Starting from v0.2.0, this repository ships as a single PyPI package (mcp-zenodo) with two sub-packages:

mcp-zenodo/
├── src/
│   ├── mcp_zenodo/          # stdio MCP server (5 tools, core)
│   │   ├── __main__.py       # entry: mcp-zenodo
│   │   ├── server.py         # FastMCP server
│   │   └── ...
│   └── mcp_zenodo_api/       # FastAPI HTTP server (11 tools, optional [api])
│       ├── __main__.py       # entry: mcp-zenodo-api
│       ├── app.py            # FastAPI app
│       └── tools/            # 11 tool modules
├── pyproject.toml
└── README.md
Sub-package Transport Tools Install Entry point
mcp_zenodo stdio (MCP SDK) 5 core tools pip install mcp-zenodo mcp-zenodo
mcp_zenodo_api HTTP (FastAPI) 11 tools pip install mcp-zenodo[api] mcp-zenodo-api

30-second quickstart

# Core stdio MCP server (Cursor IDE / Claude Desktop)
pip install mcp-zenodo

# Or with uvx (no install needed)
uvx mcp-zenodo

# Full installation with FastAPI HTTP server
pip install "mcp-zenodo[api]"

Then register the server with your MCP client. For Cursor IDE, create an mcp.json (in your project root or ~/.cursor/); for Claude Desktop, add the same block to claude_desktop_config.json:

{
  "mcpServers": {
    "Zenodo": {
      "command": "uvx",
      "args": ["mcp-zenodo"]
    }
  }
}

Restart the client; it will detect and start the Zenodo MCP server. You can then ask the assistant to search Zenodo, fetch metadata, or retrieve a citation.

Option B — FastAPI HTTP server for LangChain / LangGraph / OpenAI-compatible clients

# Install with API extras
pip install "mcp-zenodo[api]"

# Set up environment variables
cp .env.example .env
# Edit .env with your Zenodo API token

# Run the API server
mcp-zenodo-api --host 0.0.0.0 --port 8000

# Or via uvicorn directly
uvicorn mcp_zenodo_api.app:app --host 0.0.0.0 --port 8000

The FastAPI server exposes three endpoints:

  • GET /mcp/tools/openai-schema — list all 11 tools in OpenAI function-calling format
  • POST /mcp/tools/call — call a tool by name with arguments
  • POST /mcp/process — process a full MCP request through the server pipeline

Example

Ask an MCP-enabled assistant (Claude Desktop, Cursor) a question that triggers the search_records tool:

"Search Zenodo for records about climate model output and show me the top result with its DOI."

The assistant calls the search_records tool, then get_metadata, and returns a record's title, authors, DOI, and description. A representative (abbreviated) tool result looks like:

{
  "hits": [
    {
      "title": "Example Climate Model Output Dataset",
      "doi": "10.5281/zenodo.1234567",
      "type": "dataset",
      "url": "https://zenodo.org/record/1234567"
    }
  ]
}

You can then follow up with get_citation to obtain a BibTeX or APA citation, or list_files / download_file to access the record's files. (Exact fields and values depend on the live Zenodo record returned.)


Use cases

  • Literature and dataset discovery — let an AI assistant search Zenodo and surface relevant datasets, software, and papers with DOIs.
  • Citation retrieval — pull BibTeX or APA citations for records directly into a manuscript or notebook.
  • Research agents — give LangChain/LangGraph agents a Zenodo tool so they can ground answers in open research data.
  • In-editor research — query Zenodo from Cursor IDE or Claude Desktop while writing code or documentation.
  • Reproducibility workflows — locate, inspect metadata for, and download research artifacts programmatically.

Comparison and alternatives

  • vs. calling the Zenodo REST API directly — the Zenodo REST API gives full control (including deposition/upload), but you must write and maintain the integration yourself. mcp-zenodo wraps common read/retrieval operations as MCP tools so any MCP client can use them with no custom code.
  • vs. general-purpose HTTP/fetch MCP servers — a generic fetch tool can hit Zenodo URLs but has no knowledge of records, metadata, citations, or file listings. mcp-zenodo provides Zenodo-specific, typed tools.
  • vs. other research-repository MCP servers — comparable MCP servers exist for sources such as arXiv and other data repositories; mcp-zenodo is focused specifically on Zenodo. It ships two integration paths (a stdio MCP server and a FastAPI service), which lets you choose between direct MCP clients and LLM-framework/OpenAI-compatible usage.

Limitations / when NOT to use

  • Not for depositing or publishing — this project focuses on searching and retrieving from Zenodo; it does not implement Zenodo deposition/upload workflows.
  • Depends on the Zenodo API — availability, rate limits, and returned fields are governed by Zenodo; some operations may require a Zenodo API token.
  • Retrieval quality depends on Zenodo metadata — data-type detection, keyword extraction, and summaries are derived from record metadata and are best-effort.
  • Two transport modes — the stdio MCP server (mcp-zenodo) and the FastAPI HTTP server (mcp-zenodo-api) serve different use cases; pick the one matching your client.

FAQ

What is mcp-zenodo? mcp-zenodo is a Zenodo MCP server — an implementation of the Model Context Protocol that exposes Zenodo (the CERN open-access research repository) to large language models as callable tools for searching records, reading metadata, retrieving citations, and listing or downloading files.

How do I use Zenodo with Claude or ChatGPT via MCP? For Claude Desktop or Cursor IDE, install the core stdio MCP server (mcp-zenodo) via pip install mcp-zenodo or uvx mcp-zenodo, and add it to your MCP client config (claude_desktop_config.json or mcp.json) as shown in the quickstart. For OpenAI-compatible / ChatGPT-style workflows, install the FastAPI sub-package with pip install "mcp-zenodo[api]", run mcp-zenodo-api to start the HTTP service, and call its MCP-compatible tools from your framework (e.g., LangChain, LangGraph) or OpenAI-compatible client.

Which MCP clients are supported? Any MCP-compatible client can use the core stdio MCP server (mcp-zenodo) over the standard MCP transport; it is tested with Cursor IDE and works with Claude Desktop. The FastAPI sub-package (mcp-zenodo-api) targets LLM frameworks such as LangChain and LangGraph, OpenAI-compatible clients, and platforms such as LibreChat.

Do I need a Zenodo API token? The FastAPI service reads a Zenodo API token from .env (see .env.example). Some Zenodo operations work without a token, but a token is recommended for reliable access.

Is mcp-zenodo on PyPI? Yes. Starting from v0.2.0, install with pip install mcp-zenodo or uvx mcp-zenodo. The FastAPI HTTP server is available as pip install mcp-zenodo[api].


Contributing

Contributions to both implementations are welcome. Please see the implementation READMEs (mcp_sdk_core, mcp_api) for details.

About this fork

This repository is a fork of MSKazemi/mcp-zenodo, originally authored by Mohsen Seyedkazemi Ardebili.

The original project required cloning the repository and running the server manually — it did not support uvx one-click launch or PyPI distribution, making setup less convenient for end users. This fork repackages the project as a proper Python package (mcp-zenodo) published on PyPI, enabling uvx mcp-zenodo or pip install mcp-zenodo for instant use. Additional changes include:

  • Full Chinese documentation (README.zh.md)
  • Unified package structure under src/ with pyproject.toml (Hatchling build)
  • Qoder IDE integration guide
  • Deployment on CNB (cnb.cool) for better accessibility in China

Maintainer: Xiao Shishun (肖诗顺), Department of Digital Economy, Sichuan Agricultural University.


License

This project is licensed under the Apache License 2.0 — see the LICENSE file for details.


Citation

If you use mcp-zenodo in your work, please cite it. Citation metadata is provided in CITATION.cff. Example:

Seyedkazemi Ardebili, M. mcp-zenodo: A Zenodo MCP server. https://github.com/MSKazemi/mcp-zenodo

Xiao, S. mcp-zenodo (CNB fork). https://cnb.cool/xiaosicau/mcp-zenodo

Metadata

Release files for mcp-zenodo 0.2.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-zenodo 0.2.6
File Size Uploaded Provenance Actions
mcp_zenodo-0.2.6.tar.gz 31.0 kB Without provenance Details for mcp_zenodo-0.2.6.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for mcp-zenodo 0.2.6
File Interpreter ABI Platform Actions
mcp_zenodo-0.2.6-py3-none-any.whl Python 3 none any Details for mcp_zenodo-0.2.6-py3-none-any.whl

Total release size: 73.5 kB

Release files / mcp_zenodo-0.2.6.tar.gz

Download URL mcp_zenodo-0.2.6.tar.gz
Size 31.0 kB
Tags Source
SHA-256 checksum
How to use checksums
b6c89d5b06747389fde0eb130c01b06ae0cb3b5895943b67bb6c2b45a206f3fa
BLAKE2b-256 checksum
How to use checksums
8c0b131eb064d72b1c1bcc0f18b079b5eaa11a518ad820399ded823bd87534e1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Release files / mcp_zenodo-0.2.6-py3-none-any.whl

Download URL mcp_zenodo-0.2.6-py3-none-any.whl
Size 42.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d8798e8ab9e94fcbd4118bdc51fa1d80f6e2bfa6942635b3de0905ba215af99e
BLAKE2b-256 checksum
How to use checksums
760c92fe9a5e9a6da0db2612782949bab6efddb903185cc937467f6dd2f10041
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Security for mcp-zenodo 0.2.6

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page