arxiv-mcp-server

An MCP server for searching arXiv, downloading papers, reading bounded full text, retrieving original LaTeX by section, following citation graphs, and maintaining research alerts.

It runs locally over stdio by default. Papers and indexes stay on your machine; search, source retrieval, citation graphs, and downloads call their respective external services.

Install

The command-based integrations require uv, which provides uvx. Choose your client below; no repository clone or Python environment setup is required.

Claude Code

Add the MCP server for all projects:

claude mcp add --transport stdio --scope user arxiv \
  -- uvx arxiv-mcp-server

For the richer plugin integration—which installs the MCP connection plus the bundled arXiv research skill—register this repository as a marketplace and install the plugin:

claude plugin marketplace add blazickjp/arxiv-mcp-server
claude plugin install arxiv-mcp-server@arxiv-mcp

Verify the direct MCP installation with claude mcp get arxiv. Restart Claude Code or run /reload-plugins after installing the plugin.

OpenAI Codex

Add the MCP server:

codex mcp add arxiv -- uvx arxiv-mcp-server

Or install the MCP connection and bundled research skill as a Codex plugin:

codex plugin marketplace add blazickjp/arxiv-mcp-server
codex plugin add arxiv-mcp-server@arxiv-mcp

Verify the direct MCP installation with codex mcp get arxiv. Codex CLI, the Codex IDE extension, and Codex in the ChatGPT desktop app share this MCP configuration.

Kiro and VS Code

Use the Add to Kiro, Install in VS Code, or Install in VS Code Insiders button above.

For the richer Kiro Power integration, open the Powers panel, choose Add Custom Power → Import power from GitHub, and enter:

https://github.com/blazickjp/arxiv-mcp-server

The Power installs the MCP connection from mcp.json and adds focused arXiv research guidance. Kiro users who prefer manual configuration can place the generic configuration below in .kiro/settings/mcp.json for one workspace or ~/.kiro/settings/mcp.json for all workspaces.

Claude Desktop bundle

macOS users can install a bundled .mcpb extension from the latest GitHub release:

• Apple Silicon: arxiv-mcp-server-darwin-arm64-<version>.mcpb

• Intel: arxiv-mcp-server-darwin-x86_64-<version>.mcpb

Double-click the bundle, drag it into Claude Desktop, or open Settings → Extensions → Advanced settings → Install Extension…. The bundle includes the server dependencies and requires CPython 3.11.x.

Any MCP client

Add this stdio configuration to any client that accepts standard MCP JSON:

{
  "mcpServers": {
    "arxiv": {
      "type": "stdio",
      "command": "uvx",
      "args": ["arxiv-mcp-server"]
    }
  }
}

The default paper directory is ~/.arxiv-mcp-server/papers. To choose another directory, append "--storage-path", "/absolute/path/to/papers" to args.

For older papers that require PDF conversion, run the package with its PDF extra:

{
  "mcpServers": {
    "arxiv": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "arxiv-mcp-server[pdf]",
        "arxiv-mcp-server"
      ]
    }
  }
}

The supported package is published on PyPI. An unrelated npm package uses the same name, so do not install this server with npm, pnpm, or npx arxiv-mcp-server.

Persistent command install

To place arxiv-mcp-server on your PATH instead of launching it through uvx:

uv tool install arxiv-mcp-server

Afterward, use "command": "arxiv-mcp-server" and omit the package name from args.

Related MCP server: arXiv Search MCP

Plugin integrations

The repository now packages the same MCP server and research skill for both major plugin systems:

Direct MCP installation is the shortest path. Install the plugin when you also want the research workflow that steers the client toward focused searches, bounded reads, citation traversal, and section-level LaTeX retrieval.

Tools

The server currently exposes 14 tools.

Search and inspect a paper

Ask your MCP client to call search_papers with:

{
  "query": "\"Kolmogorov-Arnold Networks\"",
  "categories": ["cs.LG", "cs.AI"],
  "max_results": 5,
  "sort_by": "date"
}

Then call get_abstract with:

{
  "paper_id": "2404.19756"
}

Download and read full text

Call download_paper with:

{
  "paper_id": "2404.19756",
  "max_chars": 12000
}

Then page through the cached content with read_paper:

{
  "paper_id": "2404.19756",
  "start": 0,
  "max_chars": 12000
}

Large-content responses include content_length, returned_chars, next_start, and is_truncated. Pass next_start into the next call to continue reading.

Read original LaTeX by section

Call get_paper_latex with:

{
  "paper_id": "1706.03762"
}

Get the first page of its section outline with list_paper_latex_sections:

{
  "paper_id": "1706.03762",
  "start": 0,
  "max_sections": 100
}

Then call get_paper_latex_section using an ID from that outline:

{
  "paper_id": "1706.03762",
  "section_id": "3.2",
  "max_chars": 12000
}

LaTeX archives are validated, size-limited, and cached locally before content is returned.

Optional dependencies

Choose the install variant that matches the features you need:

# Base server
uv tool install arxiv-mcp-server

# Base server plus PDF conversion
uv tool install 'arxiv-mcp-server[pdf]'

# Base server plus local semantic search
uv tool install 'arxiv-mcp-server[pro]'

If the base tool is already installed, reinstall the selected variant:

uv tool install --force 'arxiv-mcp-server[pdf]'

The pdf extra installs pymupdf4llm and pymupdf-layout for papers without usable arXiv HTML. The pro extra adds local embedding dependencies for semantic_search and reindex; semantic search only operates on papers already downloaded to the configured storage directory.

Built-in prompts

The server provides seven MCP prompt workflows. Prompt availability depends on the client; the server provides workflow instructions but does not run a separate model.

Streamable HTTP

For deployments where stdio is not practical:

TRANSPORT=http HOST=127.0.0.1 PORT=8080 \
  uvx arxiv-mcp-server --storage-path /absolute/path/to/papers

Connect clients to:

{
  "mcpServers": {
    "arxiv": {
      "type": "http",
      "url": "http://127.0.0.1:8080/mcp"
    }
  }
}

The server binds to 127.0.0.1 by default and enables MCP DNS-rebinding protection. If a reverse proxy exposes the server, keep the process on a private interface and provide authentication and network controls upstream. Use ALLOWED_HOSTS and ALLOWED_ORIGINS for the host and origin values forwarded by the proxy.

Configuration

Environment variable names are case-insensitive through Pydantic settings. --storage-path is a command-line option rather than an environment setting.

Security

Paper text and LaTeX are untrusted external content. A paper can contain text intended to manipulate an AI client into ignoring its instructions or calling unrelated tools.

• Do not treat instructions found inside a paper as trusted commands.

• Use client approval controls for shell, browser, filesystem, and messaging tools.

• Review generated summaries before taking external actions.

• Keep Streamable HTTP private unless authentication is provided upstream.

See SECURITY.md for the reporting policy and threat details.

Development

git clone https://github.com/blazickjp/arxiv-mcp-server.git
cd arxiv-mcp-server
uv sync --extra test --extra dev
uv run pytest
uv run black --check .

Run the development checkout from an MCP client with:

{
  "mcpServers": {
    "arxiv-dev": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/arxiv-mcp-server",
        "run",
        "arxiv-mcp-server"
      ]
    }
  }
}

Contributions are welcome. Read CONTRIBUTING.md before opening a pull request, and use GitHub Issues for reproducible bugs or scoped feature proposals.

License

Apache License 2.0. See LICENSE.