Enables searching and retrieving academic papers from arXiv with advanced query capabilities including author, title, and category filters, returning structured metadata with paper summaries, PDFs, and citations.
Provides access to the DBLP computer science bibliography database for searching publications, returning detailed metadata including venue, authors, publication year, DOI, and electronic edition links.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Literature Review Assistant latest_info about transformer architectures in NLP"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A powerful Model Context Protocol (MCP) server that provides seamless access to academic literature databases, helping researchers accelerate their literature review process using LLMs and MCP clients like Claude, Cursor, and others.
arXiv Integration: Search and retrieve academic papers from arXiv
DBLP Integration: Search computer science publications from DBLP database
AI-Powered Prompts: Generate comprehensive research summaries and insights (usable as "/" commands)
MCP Compatible: Works with any MCP client (Claude, Cursor, etc.)
Structured Data: Returns well-formatted paper metadata
Fast & Reliable: Built on FastMCP for optimal performance
Extensible: Easy to add new academic databases
Related MCP server: Scholar MCP
curl -LsSf https://astral.sh/uv/install.sh | shSimply add lit-mcp to your MCP client configuration - uvx will handle the rest automatically!
Add to your MCP configuration (usually in ~/.cursor/mcp.json):
{
"mcpServers": {
"lit-mcp": {
"command": "uvx",
"args": ["lit-mcp"]
}
}
}Use this single-line command to use it with codex.
codex mcp add lit-mcp -- uvx lit-mcpAny MCP-compatible client can use lit-mcp with the same configuration pattern:
{
"mcpServers": {
"lit-mcp": {
"command": "uvx",
"args": ["lit-mcp"]
}
}
}Example Usage:
Once configured, you can use the available tools in your MCP client:
# Search tools
Search for 5 papers on "machine learning transformers" using arXiv.
Search for computer science papers on "GPS trajectory" using DBLP.
# AI-powered prompts (as "/" commands in Cursor)
/latest_info small language models
/related_topics transformer architectures
/author_spotlight computer visionSearch for academic papers on arXiv with advanced query capabilities.
Parameters:
query (string): Search query (supports arXiv syntax like au:Author_Name, ti:Title, etc.)
max_results (integer, optional): Maximum number of results (default: 10)
Returns:
List of paper objects with title, authors, publication date, summary, PDF URL, categories, and DOI
Example Queries:
# Search by author
"au:Gaurab_Chhetri"
# Search by title keywords
"ti:machine learning"
# Search by category
"cat:cs.AI"
# Combined search
"au:Chhetri AND ti:transport"Search for computer science publications in the DBLP database.
Parameters:
query (string): Search query for computer science papers
max_results (integer, optional): Maximum number of results (default: 10)
Returns:
List of publication objects with title, authors, venue, volume, number, pages, publisher, year, type, access, key, DOI, electronic edition link, and DBLP URL
Example Queries:
# Search for specific topics
"machine learning"
"computer vision"
"natural language processing"
"GPS trajectory"
"blockchain technology"Generate comprehensive summaries of the most recent innovations, trends, and papers in a research field.
Parameters:
topic (string): Research field or topic to analyze
Returns:
Well-structured Markdown document with recent papers, key trends, and insights
Features:
Identifies latest papers (preferably within last 12 months)
Focuses on highly cited, emerging, or novel works
Provides structured summaries with PDF links
Includes "Key Trends & Insights" section
Beautifully formatted for easy reading
Example Usage:
# As MCP prompt
Generate latest information about "small language models"
Analyze recent trends in "quantum machine learning"
# As "/" command in Cursor
/latest_info small language models
/latest_info quantum machine learningDiscover related and emerging research areas connected to a given topic.
Parameters:
topic (string): Research topic to explore connections for
Returns:
Structured Markdown document with related topics, representative papers, and emerging intersections
Features:
Identifies 3-6 distinct related topics or subfields
Shows connections between topics
Provides representative papers with summaries
Highlights emerging interdisciplinary areas
Reveals novel applications and fusion trends
Example Usage:
# As MCP prompt
Find related topics for "transformer architectures"
Explore connections around "federated learning"
# As "/" command in Cursor
/related_topics transformer architectures
/related_topics federated learningIdentify leading authors, labs, and research groups advancing innovation in a field.
Parameters:
topic (string): Research field to analyze for key contributors
Returns:
Structured Markdown document with top authors, their affiliations, notable papers, and collaborative networks
Features:
Ranks authors by publication frequency and impact
Shows affiliations and research themes
Lists notable papers with summaries
Identifies collaborative networks and research groups
Highlights cross-institution projects
Example Usage:
# As MCP prompt
Find leading authors in "computer vision"
Identify key researchers in "natural language processing"
# As "/" command in Cursor
/author_spotlight computer vision
/author_spotlight natural language processing{
"title": "Model Context Protocols in Adaptive Transport Systems: A Survey",
"authors": ["Gaurab Chhetri", "Shriyank Somvanshi", "..."],
"published": "2025-08-26T17:58:56+00:00",
"summary": "The rapid expansion of interconnected devices...",
"entry_id": "http://arxiv.org/abs/2508.19239v1",
"pdf_url": "http://arxiv.org/pdf/2508.19239v1",
"categories": ["cs.AI"],
"doi": null
}{
"title": "GPS Trajectory Data Mining: A Survey",
"authors": ["John Doe", "Jane Smith"],
"venue": "IEEE Transactions on Knowledge and Data Engineering",
"volume": "35",
"number": "3",
"pages": "1234-1250",
"publisher": "IEEE",
"year": "2023",
"type": "Journal Articles",
"access": "open",
"key": "journals/tkde/DoeS23",
"doi": "10.1109/TKDE.2023.1234567",
"ee": "https://doi.org/10.1109/TKDE.2023.1234567",
"url": "https://dblp.org/rec/journals/tkde/DoeS23.html"
}We tested this MCP by adding to Cursor. The output was generated using the new AI-powered prompts and search tools. This comprehensive survey demonstrates the capabilities of lit-mcp:
Generated using:
latest_info prompt for recent trends and innovations
related_topics prompt for connected research areas
author_spotlight prompt for key researchers and collaborations
arxiv_search tool for paper discovery and citations
Original prompt:
I want to write a comprehensive survey paper on small language models. Can you create me a template along with fully detailed analysis of the contents? The writeup should be narrative (paragraph) style with minimal use of bullet points. Update to the file named small-lang-models.md and put the detailed contents there. Make sure to add accurate in-text citations as well to the content using markdown citation format, and also make sure to give the PDF links to all the papers. Use the arxiv tool.
Python 3.12
uv package manager
Clone the repository
git clone https://github.com/gauravfs-14/lit-mcp.git
cd lit-mcpInstall dependencies
# Install UV if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install project dependencies
uv syncRun the MCP server
uv run lit-mcpIf you're developing locally, you can use the development setup:
{
"mcpServers": {
"lit-mcp": {
"command": "uv",
"args": [
"--directory",
"<absolute_path_to_the_cloned_repo>",
"run",
"lit-mcp"
]
}
}
}We welcome contributions! Please see our Contributing Guidelines for detailed information on how to contribute to this project.
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Make your changes
Run tests (uv run python tests/test_basic.py)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
New contributors can help with:
Adding new academic database integrations (PubMed, IEEE Xplore, ACM Digital Library)
Creating new AI-powered research prompts
Improving existing prompt templates
Adding new evaluation metrics and benchmarks
Enhancing documentation and examples
For detailed guidelines, see CONTRIBUTING.md.
This project follows a Code of Conduct to ensure a welcoming environment for all contributors.
arXiv for providing free access to academic papers
DBLP for the comprehensive computer science bibliography
arxiv-py developers for the excellent Python wrapper
DBLP API for providing direct access to computer science publications
FastMCP for the MCP server framework
If you encounter any issues or have questions:
Check the Issues page
Create a new issue with detailed information
Join our community discussions
This project is licensed under the MIT License - see the LICENSE file for details.
Search for papers on arXiv.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| max_results | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool searches for papers but doesn't describe any behavioral traits such as rate limits, authentication needs, response formats, or error handling. This leaves significant gaps for a search tool with an output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (search function) and the presence of an output schema, the description is somewhat complete but lacks details on usage guidelines and behavioral traits. It covers the basic purpose but doesn't provide enough context for optimal agent decision-making, especially with no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate, but it adds no information about parameters beyond what the schema provides. The description doesn't explain what 'query' should contain or how 'max_results' affects the search. With two parameters and no param info in the description, this meets the baseline for minimal adequacy.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search for papers on arXiv' clearly states the action (search) and resource (papers on arXiv), making the purpose immediately understandable. It distinguishes from the sibling tool 'dblp_search' by specifying the arXiv database, though it doesn't explicitly contrast them. The description avoids tautology by not merely restating the tool name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'dblp_search' or any other search options, nor does it specify contexts or exclusions for use. The agent must infer usage from the tool name and description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search DBLP database for computer science papers.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| max_results | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions searching but doesn't describe rate limits, authentication requirements, result format, or whether this is a read-only operation. The description is minimal and lacks important behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise - a single sentence that states the core purpose without any fluff. It's front-loaded with the essential information and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there's an output schema (which presumably describes the return format), the description doesn't need to explain return values. However, for a search tool with no annotations and 0% schema description coverage, the description is quite minimal and could benefit from more context about the search scope, limitations, or result characteristics.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description doesn't add any parameter-specific information beyond what's obvious from the parameter names. The description mentions 'search' which aligns with the 'query' parameter, but provides no details about query syntax, result ordering, or what 'max_results' actually controls beyond the obvious.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search') and target resource ('DBLP database for computer science papers'), making the purpose immediately understandable. However, it doesn't differentiate from the sibling tool 'arxiv_search' which likely searches a different database for similar content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus the sibling 'arxiv_search' or any other alternatives. The description simply states what it does without context about appropriate use cases or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0arxiv_searchdblp_searchScored across 2 tools
The two tools have clearly distinct purposes: one searches arXiv for papers, while the other searches DBLP for computer science papers. There is no overlap in their target databases or functionality, making them easily distinguishable.
Both tools follow a consistent naming pattern with a database prefix followed by '_search' (arxiv_search, dblp_search). This verb_noun structure is uniform and predictable across the set.
With only two tools, the server feels thin for a 'Literature Review Assistant' scope. It lacks essential operations like retrieving paper details, managing references, or accessing other databases, limiting its utility for comprehensive reviews.
The tool set is severely incomplete for literature review tasks. It only provides search functionality for two databases, missing critical operations such as fetching full-text, citation analysis, or integration with reference managers, which are core to the domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Academic paper search, scientific literature, citation analysis, arXiv & semantic related-work.
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
