Trove MCP server

trove-mcp

npm package · GitHub repo

Trove is an MCP server for academic research.

The basic idea is simple: let Claude search papers, fetch metadata, read open full text when it can, and build structured outputs on top of that.

I have tried to keep it conservative. If a provider cannot support an answer well enough, Trove returns partial, error, or unavailable instead of pretending it knows more than it does.

What it connects to

• OpenAlex (primary metadata, discovery, citations)
• Semantic Scholar (semantic recommendations and similarity)
• arXiv (preprint metadata and full text)
• Unpaywall (OA discovery by DOI)
• PubMed (biomedical indexing)
• Hugging Face Papers API (discovery context endpoints; strict trending uses citation snapshots only)
• CORE (full-text fallback)

Install (Claude Desktop, stdio)

No local install is required with npx.

Quick smoke test:

npx -y trove-mcp@latest sync --queries="graph neural network"

Optional global install:

npm i -g trove-mcp
trove-mcp sync --queries="graph neural network"

Claude Desktop on macOS

1. Open Claude Desktop.
2. Go to Settings -> Developer -> Edit Config.
3. Edit ~/Library/Application Support/Claude/claudedesktopconfig.json.
4. Add this server entry under mcpServers:

{
  "mcpServers": {
    "trove": {
      "command": "npx",
      "args": ["-y", "trove-mcp"],
      "env": {
        "TROVE_CONTACT_EMAIL": "you@example.com",
        "TROVE_DB_PATH": "/Users/you/.trove-mcp/trove.db",
        "SEMANTIC_SCHOLAR_API_KEY": "",
        "UNPAYWALL_EMAIL": "you@example.com",
        "CORE_API_KEY": ""
      }
    }
  }
}

1. Save the file and fully restart Claude Desktop.
2. Start a new chat and use Trove tools.

No API keys are required to start. Missing optional keys produce graceful partial/degraded responses.

Using with Claude

If you want Claude to use Trove, just say so in the prompt.

Examples:

• "Use Trove to find papers on speculative decoding"
• "Use Trove to compare DPO and RLHF papers"
• "Use Trove to trace the origin of LoRA"

If you do not want Claude to touch the setup-sensitive tools, hide them with TROVEDISABLEDTOOLS.

What to expect on a fresh install

• gettrendingpapers will usually return mode = unavailable on first run. Trove has to accumulate at least two local citation snapshot dates before it can compute citation velocity honestly.
• findsimilarpapers is usable without a Semantic Scholar key only in theory. In practice, reliable semantic recommendations require SEMANTICSCHOLARAPI_KEY, and Trove says so directly.
• Some papers are retrievable even when their provider coverage is incomplete. For example, an arXiv preprint may have full text but no usable reference list in Semantic Scholar or OpenAlex.

Runtime behavior

• Every tool returns a structured envelope with status, degraded, warnings, provenance, meta.version, and tool-specific data.
• Provider outages and rate limits are surfaced as warnings, not process crashes.
• Trove prefers explicit unavailability over approximate output. That is why some tools return empty results with warnings instead of "best effort" guesses.

Tools with real prerequisites

Shortened. The full README is on GitHub.