学术论文搜索

Library, Collections, Watches & Gap Analysis (require `SF_API_KEY`)

These MUTATE or read the authenticated user's account. The core read/search tools above work anonymously; these need a key.

Installation

The fastest path is npx scholar-feed-mcp@latest init, which auto-detects your client and writes the config. To set it up by hand, every client launches the same stdio server (npx -y scholar-feed-mcp@latest); only the config-file location and the wrapper key differ.

Claude Desktop (one-click) installs without editing any config: download the .mcpb bundle from the latest release and open it (or drag it into Settings > Extensions). The installer shows one optional field for a Scholar Feed API key (sf_...): leave it blank for anonymous mode (100 calls/day), or paste a free key from scholarfeed.org/settings for 1,000/day.

Claude Code takes a one-line command:

```bash

Quick Start

npx scholar-feed-mcp@latest init

This interactive wizard will: 1. Optionally ask for an API key (or skip for anonymous access) 2. Detect your MCP client (Claude Code, Cursor, or Claude Desktop) 3. Write the config and verify the connection

No API key required. Anonymous access gives you 100 calls/day, enough for a typical research session. For higher limits (1,000/day per account), get a free key at scholarfeed.org/settings.

Try asking: "Search for recent papers on test-time compute scaling"

Example Response

search_papers with q: "attention mechanism" returns:

{
  "papers": [
    {
      "arxiv_id": "2401.04088",
      "title": "Attention Is All You Need (But Not All You Get)",
      "authors": ["A. Researcher", "B. Scientist"],
      "year": 2024,
      "categories": ["cs.LG", "cs.AI"],
      "primary_category": "cs.LG",
      "arxiv_url": "https://arxiv.org/abs/2401.04088",
      "has_code": true,
      "github_url": "https://github.com/example/repo",
      "citation_count": 42,
      "rank_score": 0.73,
      "llm_summary": "Proposes a sparse attention variant that reduces compute by 60% while matching dense attention accuracy on 5 benchmarks.",
      "llm_novelty_score": 0.55
    }
  ],
  "total": 1847,
  "page": 1,
  "limit": 20,
  "next_cursor": "eyJzIjogMC43MywgImlkIjogIjI0MDEuMDQwODgifQ=="
}

Pass next_cursor back to get the next page (keyset pagination, which is more stable than page numbers for large result sets).

Environment Variables

then in your MCP config: "command": "scholar-feed-mcp", "args": []

```

Tool calls time out or fail silently Ensure Node.js 18+ is installed (node --version). Older versions lack the native fetch API.

Stale npx cache The config blocks above pin scholar-feed-mcp@latest, which re-resolves the newest version each launch. If you previously used an unpinned scholar-feed-mcp and are stuck on an old build: npx --yes scholar-feed-mcp@latest.

Windows: "command not found" Use "command": "cmd" with "args": ["/c", "npx", "-y", "scholar-feed-mcp@latest"] in your MCP config.

With an API key (1,000 calls/day per account)

claude mcp add scholar-feed -e SF_API_KEY=sf_your_key_here -- npx -y scholar-feed-mcp@latest

**Every other client** takes this standard JSON block:

To raise limits to 1,000 calls/day, add `"env": { "SF_API_KEY": "sf_your_key_here" }` to the server entry. Get a free key at [scholarfeed.org/settings](https://www.scholarfeed.org/settings).

Drop that block into the right config file:

| Client | Config file | Notes |
|--------|-------------|-------|
| Cursor | `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global) | Restart Cursor. |
| Claude Desktop | macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`; Windows: `%APPDATA%\Claude\claude_desktop_config.json` | Settings → Developer → Edit Config, then restart. |
| Windsurf | `~/.codeium/windsurf/mcp_config.json` | Cascade → MCP icon → Configure, then refresh. |
| Cline / Roo Code | `cline_mcp_settings.json` | MCP Servers sidebar icon → Configure. Cline and Roo Code share this format. |
| Gemini CLI | `~/.gemini/settings.json` (or project `.gemini/settings.json`) | |
| LM Studio | `~/.lmstudio/mcp.json` | Program tab → Install → Edit `mcp.json`. Follows Cursor's notation. |
| JetBrains (PyCharm / IntelliJ) | AI Assistant → MCP → Add → As JSON | Requires AI Assistant 2025.1+. |

A few clients need a different wrapper key or file format:

<details>
<summary><strong>VS Code (GitHub Copilot), Zed, Continue, and project-scoped configs</strong></summary>

**VS Code: GitHub Copilot** (`.vscode/mcp.json`) uses a `servers` key and an explicit `type`, and needs Copilot agent mode. You can also run `MCP: Add Server` from the Command Palette.

**Zed** (`settings.json`) uses a `context_servers` key, and the `"source": "custom"` line is required (without it, Zed silently skips the entry).

**Continue** uses YAML, with `mcpServers` as a list, in `~/.continue/config.yaml` (global) or `.continue/config.yaml` (workspace).

**Project-scoped** (`.mcp.json`), to share the server across a repo:

</details>

Windows: for any JSON config above, use "command": "cmd" and "args": ["/c", "npx", "-y", "scholar-feed-mcp@latest"].

Scholar Feed is a standard stdio MCP server, so any other MCP-compatible client works with the standard block too.

Troubleshooting

"Authentication failed: your SF_API_KEY is invalid" The key may have been revoked. Generate a new one at scholarfeed.org/settings. Or remove the key to use anonymous mode.

"Rate limit exceeded" or "Anonymous daily limit exceeded" Anonymous mode allows 100 calls/day. Get a free API key at scholarfeed.org/settings for 1,000 calls/day per account.

Server shows as "failed" with no error — especially right after an update The first launch (and the first launch after each new release) makes npx download the package. The published bin is a single self-contained file with no dependency tree to resolve, so this is fast — but on a slow link it can still outrun your client's start-up timeout, and the server then shows as "failed" with no detail. Fixes: (1) warm the cache by running it once in a terminal — npx -y scholar-feed-mcp@latest --version — then restart your client; (2) raise the MCP start-up timeout if your client supports it (Claude Code: MCP_TIMEOUT=60000). For the fastest, offline-capable launches, install once globally and point the config at it instead of npx:

```bash npm install -g scholar-feed-mcp