Skip to content
Back to search

mcp.science

Open Source MCP Servers for Scientific Research

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pathintegral-institute--mcp-science/badge.svg)](/listings/pathintegral-institute--mcp-science)

HTML

<a href="/listings/pathintegral-institute--mcp-science"><img src="/api/listings/pathintegral-institute--mcp-science/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Running any server in this repository is as simple as a single command. For example, to start the `web-fetch` server:

uvx mcp-science web-fetch

This command handles everything from installation to execution. For more details on configuration and finding other servers, see the "[How to configure MCP servers for AI client apps](#how-to-configure-mcp-servers-for-ai-client-apps)" section below.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 277 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="assets/logo_landscape.webp" width="800" />
  3. </p>
  4. <div align="center">
  5. # MCP.science: Open Source MCP Servers for Scientific Research 🔍📚
  6. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  7. _Join us in accelerating scientific discovery with AI and open-source tools!_
  8. </div>
  9. ## Quick Start
  10. Running any server in this repository is as simple as a single command. For example, to start the `web-fetch` server:
  11. ```bash
  12. uvx mcp-science web-fetch
  13. ```
  14. This command handles everything from installation to execution. For more details on configuration and finding other servers, see the "[How to configure MCP servers for AI client apps](#how-to-configure-mcp-servers-for-ai-client-apps)" section below.
  15. ## Table of Contents
  16. - [About](#about)
  17. - [What is MCP?](#what-is-mcp)
  18. - [Available servers in this repo](#available-servers-in-this-repo)
  19. - [How to integrate MCP servers into LLM](#how-to-integrate-mcp-servers-into-llm)
  20. - [How to build your own MCP server](#how-to-build-your-own-mcp-server)
  21. - [Contributing](#contributing)
  22. - [License](#license)
  23. - [Acknowledgments](#acknowledgments)
  24. - [Citation](#citation)
  25. ## About
  26. This repository contains a collection of open source [MCP](https://modelcontextprotocol.io/introduction) servers specifically designed for scientific research applications. These servers enable Al models (like Claude) to interact with scientific data, tools, and resources through a standardized protocol.
  27. ## What is MCP?
  28. > MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.
  29. >
  30. > MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:
  31. >
  32. > - A growing list of pre-built integrations that your LLM can directly plug into
  33. > - The flexibility to switch between LLM providers and vendors
  34. > - Best practices for securing your data within your infrastructure
  35. >
  36. > Source: [https://modelcontextprotocol.io/introduction](https://modelcontextprotocol.io/introduction)
  37. ## Available servers in this repo
  38. Below is a complete list of the MCP servers that live in this monorepo. Every
  39. entry links to the sub-directory that contains the server’s source code and
  40. README so that you can find documentation and usage instructions quickly.
  41. #### [Example Server](./servers/example-server/)
  42. An example MCP server that demonstrates the minimal pieces required for a
  43. server implementation.
  44. #### [Materials Project](./servers/materials-project/)
  45. A specialised MCP server that enables AI assistants to search, visualise and
  46. manipulate materials-science data from the Materials Project database. A
  47. Materials Project API key is required.
  48. #### [Python Code Execution](./servers/python-code-execution/)
  49. Runs Python code snippets in a secure, sandboxed environment with restricted
  50. standard-library access so that assistants can carry out analysis and
  51. computation without risking your system.
  52. #### [SSH Exec](./servers/ssh-exec/)
  53. Allows an assistant to run pre-validated commands on remote machines over SSH
  54. with configurable authentication and command whitelists.
  55. #### [Web Fetch](./servers/web-fetch/)
  56. Fetches and processes HTML, PDF and plain-text content from the Web so that the
  57. assistant can quote or summarise it.
  58. #### [TXYZ Search](./servers/txyz-search/)
  59. Performs Web, academic and “best effort” searches via the TXYZ API. A TXYZ API
  60. key is required.
  61. #### [Timer](./servers/timer/)
  62. A minimal countdown timer that streams progress updates to demonstrate MCP
  63. notifications.
  64. #### [GPAW Computation](./servers/gpaw-computation/)
  65. Provides density-functional-theory (DFT) calculations through the GPAW package.
  66. #### [Jupyter-Act](./servers/jupyter-act/)
  67. Lets an assistant interact with a running Jupyter kernel, executing notebook
  68. cells programmatically.
  69. #### [Mathematica-Check](./servers/mathematica-check/)
  70. Evaluates small snippets of Wolfram Language code through a headless
  71. Mathematica instance.
  72. #### [NEMAD](./servers/nemad/)
  73. Neuroscience Model Analysis Dashboard server that exposes tools for inspecting
  74. NEMAD data-sets.
  75. #### [TinyDB](./servers/tinydb/)
  76. Provides CRUD access to a lightweight JSON database backed by TinyDB so that an
  77. assistant can store and retrieve small pieces of structured data.
  78. ## How to configure MCP servers for AI client apps
  79. If you're not familiar with these stuff, here is a step-by-step guide for you: [Step-by-step guide to configure MCP servers for AI client apps](./docs/integrate-mcp-server-step-by-step.md)
  80. ### Prerequisites
  81. 1. [uv](https://docs.astral.sh/uv/) ­— a super-fast (Rust-powered) drop-in
  82. replacement for pip + virtualenv. Install it with:
  83. ```bash
  84. curl -sSf https://astral.sh/uv/install.sh | bash
  85. ```
  86. 2. An MCP-enabled client application such as
  87. [Claude Desktop](https://claude.ai/download),
  88. [VSCode](https://code.visualstudio.com/),
  89. [Goose](https://block.github.io/goose/),
  90. [5ire](https://5ire.app/).
  91. ### The short version – use `uvx`
  92. Any server in this repository can be launched with a single shell command. The
  93. pattern is:
  94. ```bash
  95. uvx mcp-science <server-name>
  96. ```
  97. For example, to start the `web-fetch` stdio server locally, configure the following command in your client:
  98. ```bash
  99. uvx mcp-science web-fetch
  100. ```
  101. Which corresponds to this in claude desktop's json configuration:
  102. ```json
  103. {
  104. "mcpServers": {
  105. "web-fetch": {
  106. "command": "uvx",
  107. "args": [
  108. "mcp-science",
  109. "web-fetch"
  110. ]
  111. }
  112. }
  113. }
  114. ```
  115. The command will download the `mcp-science` package from PyPI and run the requested entry-point.
  116. #### Find other servers
  117. Have a look at the [Available servers](#available-servers-in-this-repo) list —
  118. every entry in the table works with the pattern shown above.
  119. ---
  120. ### Optional: managing integrations with MCPM
  121. [MCPM](https://mcpm.sh/) is a convenience command-line tool that can automate
  122. the process of wiring servers into supported clients. It is not required but
  123. can be useful if you frequently switch between clients or maintain a large
  124. number of servers.
  125. The basic workflow is:
  126. ```bash
  127. # Install mcpm first – it is a separate project
  128. uv pip install mcpm
  129. mcpm client ls # discover supported clients
  130. mcpm client set <name> # pick the one you are using
  131. # Add a server (automatically installing it if needed)
  132. mcpm add web-fetch
  133. ```
  134. After the command finishes, restart your client so that it reloads its tool
  135. configuration. You can browse the [MCPM Registry](https://mcpm.sh/registry/)
  136. for additional community-maintained servers.
  137. ## How to build your own MCP server
  138. Please check [How to build your own MCP server step by step](./docs/how-to-build-your-own-mcp-server-step-by-step.md) for more details.
  139. ## Contributing
  140. We enthusiastically welcome contributions to MCP.science! You can help with improving the existing servers, adding new servers, or anything that you think will make this project better.
  141. If you are not familiar with GitHub and how to contribute to a open source repository, then it might be a bit of challenging, but it's still easy for you. We would recommend you to read these first:
  142. - [How to make your first pull request on GitHub](https://www.freecodecamp.org/news/how-to-make-your-first-pull-request-on-github-3/)
  143. - [Creating a pull request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request?tool=webui)
  144. In short, you can follow these steps:
  145. 1. Fork the repository to your own GitHub account
  146. 2. Clone the forked repository to your local machine
  147. 3. Create a feature branch (`git checkout -b feature/amazing-feature`)
  148. 4. Make your changes and commit them (`git commit -m 'Add amazing feature'`)
  149. <details>
  150. <summary>👈 Click to see more conventions about directory and naming</summary>
  151. Please create your new server in the `servers` folder.
  152. For creating a new server folder under repository folder, you can simply run (replace `your-new-server` with your server name)
  153. ```sh
  154. uv init --package --no-workspace servers/your-new-server
  155. uv add --directory servers/your-new-server mcp
  156. ```
  157. This will create a new server folder with the necessary files:
  158. ```bash
  159. servers/your-new-server/
  160. ├── README.md
  161. ├── pyproject.toml
  162. └── src
  163. └── your_new_server
  164. └── __init__.py
  165. ```
  166. You may find there are 2 related names you might see in the config files:
  167. 1. **Project name** (hyphenated): The folder, project name and script name in `pyproject.toml`, e.g. `your-new-server`.
  168. 2. **Python package name** (snake_case): The folder inside `src/`, e.g. `your_new_server`.
  169. </details>
  170. 5. Push to the branch (`git push origin feature/amazing-feature`)
  171. 6. Open a Pull Request
  172. Please make sure your PR adheres to:
  173. - Clear commit messages
  174. - Proper documentation updates
  175. - Test coverage for new features
  176. ### Contributor Recognition in Subrepos
  177. If you want to recognize contributors for a specific server/subrepo (e.g. `servers/gpaw-computation/`), you can use the [All Contributors CLI](https://allcontributors.org/docs/en/cli/installation) in that subdirectory.
  178. **Steps:**
  179. 1. In your subrepo (e.g. `servers/gpaw-computation/`), create a `.all-contributorsrc` file (see [example](servers/gpaw-computation/.all-contributorsrc)).
  180. 2. Add contributors using the CLI:
  181. ```bash
  182. npx all-contributors add <github-username> <contribution-type>
  183. ```
  184. 3. Generate or update the contributors section in the subrepo's `README.md`:
  185. ```bash
  186. npx all-contributors generate
  187. ```
  188. 4. Commit the changes to the subrepo's `README.md` and `.all-contributorsrc`.
  189. For more details, see the [All Contributors CLI installation guide](https://allcontributors.org/docs/en/cli/installation).
  190. ## License
  191. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
  192. ## Acknowledgments
  193. Thanks to all contributors!
  194. ## Citation
  195. For general use, please cite this repository as described in the root [CITATION.cff](./CITATION.cff).
  196. If you use a specific server/subproject, please see the corresponding `CITATION.cff` file in that subproject's folder under `servers/` for the appropriate citation.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.