ToolUniverse
MCP server by mims-harvard
Give AI assistants access to thousands of scientific tools, databases and literature sources for life science and research work.
Install ToolUniverse
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
OPENAI_API_KEYsecret optional OpenAI API key for LLM-based tool finding and embedding featuresANTHROPIC_API_KEYsecret optional Anthropic API key for Claude-based featuresGEMINI_API_KEYsecret optional Google Gemini API key for Gemini-based featuresOPENROUTER_API_KEYsecret optional OpenRouter API key for accessing 100+ LLM modelsAZURE_OPENAI_API_KEYsecret optional Azure OpenAI API key (alternative to OpenAI)HF_TOKENsecret optional HuggingFace token for accessing models and datasets
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/tooluniverseAbout
ToolUniverse is a catalog of scientific tools for AI scientist workflows, covering machine learning models, datasets, APIs and scientific packages. It supports literature search across PubMed, Semantic Scholar, ArXiv, BioRxiv and Europe PMC, plus life science databases for genes, diseases, proteins and drugs. A compact mode reduces the large tool set to a few discovery tools to save context.
It runs locally over stdio from the PyPI package tooluniverse, started with uvx. It needs Python 3.10 or newer. No API key is required to start. Optional keys (NCBI, Semantic Scholar, BioGRID, DisGeNET, OMIM, OncoKB, OpenAI, Anthropic, Gemini, HuggingFace) raise rate limits or enable extra features.
What you can do
- Search literature across PubMed, Semantic Scholar, ArXiv, BioRxiv and Europe PMC
- Query gene, disease, protein interaction and oncology databases
- Discover tools through a compact mode with a few core discovery tools
- Run long tasks asynchronously with progress tracking
- Chain tools into sequential or parallel workflows
- Cache results locally for repeat queries and offline use
Tools
Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.
Example prompts
Find recent PubMed papers on KRAS inhibitors in lung cancer
Which genes are associated with Marfan syndrome according to DisGeNET?
List protein interaction partners of TP53 from BioGRID
Search ArXiv and BioRxiv for preprints on protein structure prediction
Set up
Every client starts ToolUniverse on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio tooluniverse --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "AZURE_OPENAI_API_KEY=<YOUR_AZURE_OPENAI_API_KEY>" --env "HF_TOKEN=<YOUR_HF_TOKEN>" --env "NCBI_API_KEY=<YOUR_NCBI_API_KEY>" --env "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uvx tooluniverse- Start Claude Code and type
/mcp. tooluniverse should show as connected.
Add --scope user to make it available in every project. Replace the placeholders with your own values.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"tooluniverse": {
"command": "uvx",
"args": [
"tooluniverse"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"AZURE_OPENAI_API_KEY": "<YOUR_AZURE_OPENAI_API_KEY>",
"HF_TOKEN": "<YOUR_HF_TOKEN>",
"NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}- Save the file and restart Claude Desktop. Replace the placeholders with your own values.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"tooluniverse": {
"command": "uvx",
"args": [
"tooluniverse"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"AZURE_OPENAI_API_KEY": "<YOUR_AZURE_OPENAI_API_KEY>",
"HF_TOKEN": "<YOUR_HF_TOKEN>",
"NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}Needs uv (Python) on your computer. Replace the placeholders with your own values.
VS Code
Add it to .vscode/mcp.json. VS Code asks for the secret the first time and stores it securely:
{
"servers": {
"tooluniverse": {
"type": "stdio",
"command": "uvx",
"args": [
"tooluniverse"
],
"env": {
"OPENAI_API_KEY": "${input:openai-api-key}",
"ANTHROPIC_API_KEY": "${input:anthropic-api-key}",
"GEMINI_API_KEY": "${input:gemini-api-key}",
"OPENROUTER_API_KEY": "${input:openrouter-api-key}",
"AZURE_OPENAI_API_KEY": "${input:azure-openai-api-key}",
"HF_TOKEN": "${input:hf-token}",
"NCBI_API_KEY": "${input:ncbi-api-key}",
"SEMANTIC_SCHOLAR_API_KEY": "${input:semantic-scholar-api-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "openai-api-key",
"description": "OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "anthropic-api-key",
"description": "ANTHROPIC_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "gemini-api-key",
"description": "GEMINI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "openrouter-api-key",
"description": "OPENROUTER_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "azure-openai-api-key",
"description": "AZURE_OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "hf-token",
"description": "HF_TOKEN",
"password": true
},
{
"type": "promptString",
"id": "ncbi-api-key",
"description": "NCBI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "semantic-scholar-api-key",
"description": "SEMANTIC_SCHOLAR_API_KEY",
"password": true
}
]
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"tooluniverse": {
"command": "uvx",
"args": [
"tooluniverse"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"AZURE_OPENAI_API_KEY": "<YOUR_AZURE_OPENAI_API_KEY>",
"HF_TOKEN": "<YOUR_HF_TOKEN>",
"NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}- Refresh the MCP server list in Cascade. Replace the placeholders with your own values.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add tooluniverse --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "AZURE_OPENAI_API_KEY=<YOUR_AZURE_OPENAI_API_KEY>" --env "HF_TOKEN=<YOUR_HF_TOKEN>" --env "NCBI_API_KEY=<YOUR_NCBI_API_KEY>" --env "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uvx tooluniverseOr edit ~/.codex/config.toml directly:
[mcp_servers.tooluniverse]
command = "uvx"
args = ["tooluniverse"]
env = { OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>", ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>", GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>", OPENROUTER_API_KEY = "<YOUR_OPENROUTER_API_KEY>", AZURE_OPENAI_API_KEY = "<YOUR_AZURE_OPENAI_API_KEY>", HF_TOKEN = "<YOUR_HF_TOKEN>", NCBI_API_KEY = "<YOUR_NCBI_API_KEY>", SEMANTIC_SCHOLAR_API_KEY = "<YOUR_SEMANTIC_SCHOLAR_API_KEY>" }Needs uv (Python) on your computer. Replace the placeholders with your own values.
Gemini CLI
gemini mcp add -e "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" -e "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" -e "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" -e "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" -e "AZURE_OPENAI_API_KEY=<YOUR_AZURE_OPENAI_API_KEY>" -e "HF_TOKEN=<YOUR_HF_TOKEN>" -e "NCBI_API_KEY=<YOUR_NCBI_API_KEY>" -e "SEMANTIC_SCHOLAR_API_KEY=<YOUR_SEMANTIC_SCHOLAR_API_KEY>" tooluniverse uvx tooluniverseThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"tooluniverse": {
"command": "uvx",
"args": [
"tooluniverse"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"AZURE_OPENAI_API_KEY": "<YOUR_AZURE_OPENAI_API_KEY>",
"HF_TOKEN": "<YOUR_HF_TOKEN>",
"NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer. Replace the placeholders with your own values.
Embed
Show ToolUniverse in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/tooluniverse)<a href="https://mcp.tc/i/tooluniverse"><img src="https://mcp.tc/i/tooluniverse/badge.svg" alt="ToolUniverse on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/tooluniverse.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/tooluniverse" title="ToolUniverse on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/tooluniverse.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the ToolUniverse card to your site.
Add the mcp.tc card for ToolUniverse, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/tooluniverse.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="tooluniverse"><a href="https://mcp.tc/i/tooluniverse">ToolUniverse on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/tooluniverse)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
FAQ
Can I paste mcp.tc/i/tooluniverse into my MCP client?
No. ToolUniverse runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx tooluniverse.
Does ToolUniverse need an API key?
Yes. It reads OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, OPENROUTER_API_KEY, AZURE_OPENAI_API_KEY, HF_TOKEN, NCBI_API_KEY and SEMANTIC_SCHOLAR_API_KEY from its environment, and OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, OPENROUTER_API_KEY, AZURE_OPENAI_API_KEY, HF_TOKEN, NCBI_API_KEY and SEMANTIC_SCHOLAR_API_KEY are secrets. Put the values in your client’s config on your own machine, never in a shared file.
Is ToolUniverse a remote or a local server?
Local. Your client starts it as a process on your computer with uvx tooluniverse, which needs uv (Python).
What can ToolUniverse do?
You can search literature across PubMed, Semantic Scholar, ArXiv, BioRxiv and Europe PMC, query gene, disease, protein interaction and oncology databases and discover tools through a compact mode with a few core discovery tools.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to ToolUniverse?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read ToolUniverse’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with mims-harvard. This page was built from ToolUniverse’s public metadata, last checked on 6 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.