PubMed MCP server
Biomedical literature search on PubMed. Add one address to your AI assistant and it can call the tool below itself, with your FoxAPIs key. It costs the same credits as the REST API, and an answer with no data is not charged.
Server address
https://foxapis.com/mcp/data/pubmed
Streamable HTTP, bearer key in the Authorization header. This address carries only the PubMed tool; https://foxapis.com/mcp/data carries all of them, and ?source=pubmed,github picks several.
What you can ask
Five prompts to give your assistant once the server is added:
- Find recent PubMed papers on CRISPR gene editing and list titles, journals and dates.
- Search PubMed for studies on intermittent fasting published since 2024.
- What does PubMed return for 'long covid fatigue'? Give me the three newest papers.
- List the authors of recent PubMed papers on mRNA vaccines.
- Find PubMed papers about gut microbiome and depression and summarize the titles.
The tool your assistant gets
| Tool | What it returns | Inputs | Credits a call |
|---|---|---|---|
pubmed_search | Search PubMed by keyword; returns papers with title, authors, journal, date and PubMed link. | query (required), max_results, sort, date_from | 5 |
Credits come from the same file as the pricing page. Plans and top-ups are on pricing.
Set it up
Use your FoxAPIs key (it starts with fxp_) as the bearer token. Get one free at foxapis.com/trial.
Claude Code
Run in a terminal. Its docs.
claude mcp add --transport http foxapis-data https://foxapis.com/mcp/data/pubmed \ --header "Authorization: Bearer YOUR_KEY"
The Claude Code docs show this form (--transport http, name, URL, --header) for a server that takes a bearer token.
Cursor
.cursor/mcp.json in a project, or ~/.cursor/mcp.json for every project. Its docs.
{
"mcpServers": {
"foxapis-data": {
"url": "https://foxapis.com/mcp/data/pubmed",
"headers": {
"Authorization": "Bearer YOUR_KEY"
}
}
}
}Cursor's remote-server example uses a url and a headers object.
VS Code (Copilot)
.mcp.json at the workspace root, or ~/.copilot/mcp-config.json. Its docs.
{
"mcpServers": {
"foxapis-data": {
"type": "http",
"url": "https://foxapis.com/mcp/data/pubmed",
"headers": {
"Authorization": "Bearer YOUR_KEY"
},
"tools": [
"*"
]
}
}
}Do not store a real key in a file you share.
Cline
cline_mcp_settings.json (open it from Cline's MCP Servers panel). Its docs.
{
"mcpServers": {
"foxapis-data": {
"type": "streamableHttp",
"url": "https://foxapis.com/mcp/data/pubmed",
"headers": {
"Authorization": "Bearer YOUR_KEY"
},
"disabled": false,
"autoApprove": []
}
}
}Cline's docs say that leaving type out selects the older SSE transport, so keep type.
Zed
settings.json (Zed: open settings). Its docs.
{
"context_servers": {
"foxapis-data": {
"url": "https://foxapis.com/mcp/data/pubmed",
"headers": {
"Authorization": "Bearer YOUR_KEY"
}
}
}
}
n8n
an MCP Client Tool node in a workflow. Its docs.
Endpoint: https://foxapis.com/mcp/data/pubmed Server transport: HTTP Streamable Authentication: Header Auth Name: Authorization Value: Bearer YOUR_KEY
Not run by us: the fields are the ones n8n's MCP Client Tool documents. The server speaks Streamable HTTP.
Claude Desktop and ChatGPT
Not covered here: their custom-connector screens ask for sign-in (OAuth) or no authentication, and this server takes a bearer key in a header, so it works best in the clients above. We have not tested it in either.
A real answer
The pubmed_search tool called once through a real MCP client session on 20 November 2026 with the input {"query":"crispr","max_results":3}. Long text is cut and lists are cut to three items for display; it is not invented.
{
"query": "crispr",
"total_results": 72892,
"returned": 3,
"papers": [
{
"pmid": "25315507",
"title": "Genome modification by CRISPR/Cas9",
"authors": [
"Ma Y",
"Zhang L",
"Huang X"
],
"author_count": 3,
"journal": "The FEBS journal",
"pub_date": "2014 Dec",
"epub_date": "2014 Nov 7",
"article_type": [
"Journal Article",
"Research Support, Non-U.S. Gov't",
"Review"
],
"doi": "10.1111/febs.13110",
"pubmed_url": "https://pubmed.ncbi.nlm.nih.gov/25315507/",
"abstract_available": true
},
{
"pmid": "27699445",
"title": "CRISPR/Cas9 Immune System as a Tool for Genome Engineering",
"authors": [
"Hryhorowicz M",
"Lipiński D",
"Zeyland J"
],
"author_count": 4,
"journal": "Archivum immunologiae et therapiae experimentalis",
"pub_date": "2017 Jun",
"epub_date": "2016 Oct 3",
"article_type": [
"Journal Article",
"Review"
],
"doi": "10.1007/s00005-016-0427-5",
"pmc_id": "PMC5434172",
"pubmed_url": "https://pubmed.ncbi.nlm.nih.gov/27699445/",
"abstract_available": true
},
{
"pmid": "31727474",
"title": "CRISPR/Cas System: Recent Advances and Future Prospects for Genome Editing",
"authors": [
"Manghwar H",
"Lindsey K",
"Zhang X"
],
"author_count": 4,
"journal": "Trends in plant science",
"pub_date": "2019 Dec",
"epub_date": "2019 Nov 11",
"article_type": [
"Journal Article",
"Research Support, Non-U.S. Gov't",
"Review"
],
"doi": "10.1016/j.tplants.2019.09.006",
"pubmed_url": "https://pubmed.ncbi.nlm.nih.gov/31727474/",
"abstract_available": true
}
],
"pubmed_search_url": "https://pubmed.ncbi.nlm.nih.gov/?term=crispr"
}
Charged: 5 credits.
Try it free
Runs the pubmed_search call with the sample input below. No key and no sign-up; a few runs a day per visitor.
{
"query": "crispr",
"max_results": 3
}
Other data-source MCP servers
bioRxiv · ClinicalTrials.gov · FDA · Steam · Apple App Store · Google Play · all of them
Free to start: 100 credits, no card. Then from $10. Credits you buy never expire.
Get my free keyThe same data over REST: PubMed search. More: all MCP servers · people and company tools