MCP Server for Scientific Paper Harvesting from arXiv and OpenAlex
Scientific papers mcp mcp server connects Scientific Papers MCP to AI assistants that speak the Model Context Protocol. MCP Server for Scientific Paper Harvesting from arXiv and OpenAlex.
A comprehensive Model Context Protocol (MCP) server that provides LLMs with real-time access to scientific papers from 6 major academic sources: arXiv, OpenAlex, PMC (PubMed Central), Europe PMC, bioRxiv/medRxiv, and CORE.
Once connected, the assistant can call these 6 tools directly:
list_categories — The list_categories tool exposed by this serverfetch_latest — Fetches the latest papers from any source for a given category with metadata only (no text extraction)fetch_top_cited — Fetches the top cited papers from OpenAlex for a given concept since a specific datesearch_papers — Searches for papers across multiple academic sources with field-specific search and sorting optionsfetch_content — Fetches full metadata and text content for a specific paper by ID with complete text extractionBuild — The Build tool exposed by this serverThe server is distributed via npm as npm, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply one environment variable: CORE_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Scientific Papers MCP sits in that group, and the shape of its toolset — list_categories, fetch_latest, fetch_top_cited among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| list_categories | The list_categories tool exposed by this server. |
| fetch_latest | Fetches the latest papers from any source for a given category with **metadata only** (no text extraction). |
| fetch_top_cited | Fetches the top cited papers from OpenAlex for a given concept since a specific date. |
| search_papers | Searches for papers across multiple academic sources with field-specific search and sorting options. |
| fetch_content | Fetches full metadata and text content for a specific paper by ID with **complete text extraction**. |
| Build | The Build tool exposed by this server. |
{
"mcpServers": {
"scientific-papers": {
"command": "latest-science-mcp"
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| CORE_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.