[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/adityak74-mcp-scholarly-badge.png)](https://mseep.ai/app/adityak74-mcp-scholarly)

# mcp-scholarly MCP server
[![smithery badge](https://smithery.ai/badge/mcp-scholarly)](https://smithery.ai/server/mcp-scholarly)

A MCP server to search for accurate academic articles. More scholarly vendors will be added soon.

## Search tools

- `search-arxiv` — arXiv search (no key needed)
- `search-google-scholar` — Google Scholar via the `scholarly` library (free proxy pool)
- `search-google-web` — Google web search via the [SerpBase API](https://serpbase.dev). Optional; only registered when `SERPBASE_API_KEY` is set. Get a key at https://serpbase.dev/dashboard/api-keys (free tier available).

![demo1.jpeg](examples/demo1.png)

![image](https://github.com/user-attachments/assets/13202184-bc12-4530-b7c1-2ee698f3e1cc)

<a href="https://glama.ai/mcp/servers/aq05b2p0ql"><img width="380" height="200" src="https://glama.ai/mcp/servers/aq05b2p0ql/badge" alt="Scholarly Server MCP server" /></a>

![star-history-202551](https://github.com/user-attachments/assets/f22d5796-017c-4c53-b230-101a09a28118)


## Components

### Tools

The server implements one tool:
- search-arxiv: Search arxiv for articles related to the given keyword.
  - Takes "keyword" as required string arguments

## Quickstart

### Install

#### Claude Desktop

On MacOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`

<details>
  <summary>Development/Unpublished Servers Configuration</summary>
  ```
  "mcpServers": {
    "mcp-scholarly": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly",
        "run",
        "mcp-scholarly"
      ]
    }
  }
  ```
</details>

<details>
  <summary>Published Servers Configuration</summary>
  ```
  "mcpServers": {
    "mcp-scholarly": {
      "command": "uvx",
      "args": [
        "mcp-scholarly"
      ]
    }
  }
  ```
</details>

or if you are using Docker

<details>
  <summary>Published Docker Servers Configuration</summary>
  ```
  "mcpServers": {
    "mcp-scholarly": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "mcp/scholarly"
      ]
    }
  }
  ```
</details>

### Installing via Smithery

To install mcp-scholarly for Claude Desktop automatically via [Smithery](https://smithery.ai/server/mcp-scholarly):

```bash
npx -y @smithery/cli install mcp-scholarly --client claude
```

## Development

### Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:
```bash
uv sync
```

2. Build package distributions:
```bash
uv build
```

This will create source and wheel distributions in the `dist/` directory.

3. Publish to PyPI:
```bash
uv publish
```

Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token: `--token` or `UV_PUBLISH_TOKEN`
- Or username/password: `--username`/`UV_PUBLISH_USERNAME` and `--password`/`UV_PUBLISH_PASSWORD`

### Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging
experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector).


You can launch the MCP Inspector via [`npm`](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with this command:

```bash
npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarly
```


Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

## Using with zorp

[zorp](https://github.com/aviskaar/zorp) needs a search-capable MCP tool
before `validate` will run. This server satisfies that check, because zorp
matches on a search verb in the tool name and these tools are called
`search-arxiv` and `search-google-scholar`.

```bash
zorp-agent --yes \
  --mcp "stdio:scholarly:uv:run:mcp-scholarly" \
  validate "<your research question>"
```

Or configure it once, so every run picks it up:

```toml
# .zorp/mcp.toml
[[server]]
name = "scholarly"
transport = "stdio"
command = "uv"
args = ["run", "mcp-scholarly"]
trust = "sandbox"
timeout_secs = 60
```

Notes measured against zorp's transport, not assumed:

- `search-arxiv` answers in about 1 second. zorp's default stdio read
  budget is 30 seconds, so the default is comfortable. `timeout_secs = 60`
  above is headroom for `search-google-scholar`, which goes through
  `scholarly` and a free proxy pool and is far less predictable.
- Logging goes to stderr. Nothing but JSON-RPC reaches stdout, which is
  what zorp's newline-delimited framing requires.
- An empty keyword comes back as an MCP tool error rather than an empty
  result set. zorp cares about that distinction: a failed search that
  looks like "no prior work" would put a wrong novelty score into an
  evidence record.
- arxiv returns best-effort matches for any query, including nonsense, so
  a non-empty result set is not by itself evidence that prior work exists.
  The tool description says so, since that is the text the model reads.