Lit

Provides access to arXiv and DBLP data with AI prompts for literature reviews.

typescript

1

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gauravfs-14-lit-mcp": {
      "command": "uvx",
      "args": [
        "lit-mcp"
      ]
    }
  }
}

lit-mcp is a dedicated MCP server that provides access to academic literature databases and AI-powered prompts to assist you with literature reviews. It connects to sources like arXiv and DBLP, returns structured paper metadata, and works with any MCP client to streamline your research workflow.

How to use

You use lit-mcp by configuring it in your MCP client so the client can launch and communicate with the server. Once configured, you can search for papers from arXiv and DBLP, generate AI-powered summaries, and explore related topics or author spotlights. Use the available tools to discover papers, extract metadata, and receive structured results suitable for inclusion in literature surveys or review drafts.

How to install

Prerequisites: you need a working JavaScript/TypeScript runtime for MCP tooling, and the UV package manager to run MCP servers.

# Install UV (one-time setup)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Start the lit-mcp server via UV (recommended runtime)
uv run lit-mcp

# Add lit-mcp to your MCP client configuration so uvx handles the rest automatically

*** MCP client integration examples are provided below to help you wire lit-mcp into common clients. ***

## Additional notes

Two standard startup configurations are shown to integrate lit-mcp with MCP clients. Use the provided patterns exactly as written to ensure the client launches lit-mcp correctly.

{ "mcpServers": { "lit-mcp": { "command": "uvx", "args": ["lit-mcp"] } } }


You can also start lit-mcp directly via the core runtime, which is demonstrated as:
```uv run lit-mcp```

{ "mcpServers": { "lit-mcp": { "command": "uvx", "args": ["lit-mcp"] } } }


## Available tools

### arxiv\_search

Query arXiv for papers with advanced parameters such as author, title keywords, or category, returning structured results including title, authors, date, summary, PDF link, categories, and DOI.

### dblp\_search

Query DBLP for computer science publications, returning structured results including title, authors, venue, year, DOI, and URLs.

### latest\_info

Generate comprehensive, well-structured summaries of recent advances and trends in a chosen research topic, with key insights and PDF links.

### related\_topics

Identify 3–6 related topics or subfields connected to a given topic, showing connections and representative papers.

### author\_spotlight

Highlight leading authors, labs, and research groups, including affiliations and notable papers, with collaboration networks.