600,000+ CS/AI/ML papers in your AI assistant: search, novelty scores, citations, daily watches.
Scholar Feed MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. 600,000+ CS/AI/ML papers in your AI assistant: search, novelty scores, citations, daily watches.
Scholar Feed is a research-discovery engine for computer science and AI/ML papers, founded in 2025. It indexes 600,000+ papers from arXiv — ranked by novelty, citation velocity, and relevance — with LLM-generated summaries, a citation graph, author profiles, and full-text extraction. It is available as a website, a public REST API, and a Model Context Protocol (MCP) server that AI agents can call directly. This package (scholar-feed-mcp) is the open-source MCP server.
Once Scholar Feed is connected, these are the calls the assistant has available:
name — scholar-feedscholar-feed — mcp@latestClient — Config fileCursor — .cursor/mcp.json (project) or ~/.cursor/mcp.json (global)Windsurf — ~/.codeium/windsurf/mcp_config.jsonsave_paper — Bookmark a paper to your library (idempotent; feeds personalization)unsave_paper — Remove a paper from your library (idempotent)like_paper — "More like this" calibration signal for the For You feed (insert-only)list_library — List your saved papers, newest firstlist_collections — List collections with paper countscreate_collection — Create a named collection (get-or-create; no error on duplicate)add_to_collection — Add a paper to a collection by name or id (also auto-saves)scholar-feed-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need 2 environment variables: SF_API_KEY, SF_API_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Scholar Feed's toolset — name, scholar-feed, Client and 11 more — is a fair guide to whether it matches your workflow. It is maintained by YGao2005; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| name | scholar-feed |
| scholar-feed | mcp@latest |
| Client | Config file |
| Cursor | .cursor/mcp.json (project) or ~/.cursor/mcp.json (global) |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
| save_paper | Bookmark a paper to your library (idempotent; feeds personalization). |
| unsave_paper | Remove a paper from your library (idempotent). |
| like_paper | "More like this" calibration signal for the For You feed (insert-only). |
| list_library | List your saved papers, newest first. |
| list_collections | List collections with paper counts. |
| create_collection | Create a named collection (get-or-create; no error on duplicate). |
| add_to_collection | Add a paper to a collection by name or id (also auto-saves). |
| remove_from_collection | Remove a paper from a collection (stays saved). |
| create_watch | Standing daily-evaluated saved search; get-or-create by name. Define it with a structured criteria filter (recommended) or a single seed selector. |
{
"mcpServers": {
"scholar-feed": {
"command": "npx",
"args": ["-y", "scholar-feed-mcp"],
"env": {
"SF_API_KEY": "your-value",
"SF_API_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| SF_API_KEY | Credential the server authenticates with. | Yes |
| SF_API_BASE_URL | Endpoint or connection string the server talks to. | 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.