AI Research Assistant MCP
Provides tools for discovering, retrieving, and analyzing academic papers from arXiv, including search, detailed paper retrieval, summarization, comparison, methodology extraction, limitation analysis, and research gap identification.
Uses Google Gemini for AI-powered research analysis, enabling structured summarization, paper comparison, methodology explanation, limitation analysis, and research gap discovery on academic papers.
Click on "Deploy 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., "@AI Research Assistant MCP Find recent papers on retrieval augmented generation and identify potential research gaps."
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.
AI Research Assistant MCP
An MCP-powered AI research assistant for discovering, understanding, comparing, and organizing academic papers.
The server connects to arXiv for paper discovery and uses Gemini to perform research-oriented analysis. It is designed to help researchers move from finding papers to understanding their methods, limitations, and potential research gaps.
Features
π Paper Discovery
Search arXiv using a research topic or keyword.
The server returns:
Paper title
Authors
Abstract
Publication date
Updated date
arXiv URL
PDF URL
π Paper Retrieval
Retrieve detailed information about a specific paper using its arXiv ID or URL.
π Paper Summarization
Generate a structured research-oriented summary covering:
Research problem
Proposed approach
Key results
Main contribution
Why the work matters
βοΈ Paper Comparison
Compare multiple papers across:
Research problem
Core method
Model/retrieval architecture
Dataset or evaluation
Results
Strengths
Weaknesses
Differences
Common findings
Research opportunities
π¬ Methodology Analysis
Extract and explain the methodology of a paper, including:
Research objective
Architecture
Main technique
Data used
Training/retrieval process
Evaluation method
Technical components
β οΈ Limitation Analysis
Analyze papers for:
Explicit limitations
Methodological weaknesses
Evaluation limitations
Dataset limitations
Generalization concerns
Computational concerns
Future research questions
The assistant distinguishes between limitations explicitly supported by the paper and potential research questions inferred from the available information.
π‘ Research Gap Discovery
Given a research topic and multiple papers, identify potential research gaps and provide:
Gap
Evidence from the literature
Why the gap matters
Possible research question
Possible experiment
Expected contribution
The system is instructed not to present an unverified gap as an established fact.
πΎ Research Library
Papers can be saved locally to create a personal research library.
Available operations include:
Save a paper
List saved papers
Search saved papers
Saved papers are stored in saved_papers.json.
Related MCP server: LitSynth MCP Server
Architecture
AI Client
β
β MCP
βΌ
βββββββββββββββββββββββ
β AI Research β
β Assistant Server β
ββββββββββββ¬βββββββββββ
β
βββββββββ΄βββββββββ
β β
βΌ βΌ
arXiv Gemini
Paper Search AI Analysis
β β
βββββββββ¬βββββββββ
βΌ
Research InsightsThe server is implemented with FastMCP and exposes research capabilities as MCP tools.
MCP Tools
The current server provides:
search_papers() get_paper() summarize_paper() compare_papers() extract_methodology() extract_limitations() find_research_gaps() save_paper() list_saved_papers() search_saved_papers()
Technology Stack
Python 3.11+
FastMCP
Model Context Protocol (MCP)
arXiv API
Google Gemini API
Requests
JSON-based local storage
Project Structure
research-assistant/
β
βββ src/
β βββ research_assistant/
β βββ __init__.py
β
βββ server.py
βββ pyproject.toml
βββ README.md
βββ .gitignore
βββ .python-versionSetup
Install the project dependencies with:
uv syncSet your Gemini API key as an environment variable:
GEMINI_API_KEY=your_api_keyDo not commit API keys or .env files to GitHub.
Running the Server
Run the MCP server locally:
uv run server.pyTesting with MCP Inspector
Run:
uv run fastmcp dev inspector server.pyThe MCP Inspector can then be used to test the available tools and verify their responses.
Example Workflow
A typical research workflow can look like:
Research Topic β Search Papers β Select Relevant Papers β Retrieve Paper Details β Summarize Papers β Compare Papers β Analyze Methodology β Analyze Limitations β Identify Potential Research Gaps β Save Important Papers
For example: text "Find papers about retrieval augmented generation and identify potential research gaps."
The assistant can search the literature, retrieve relevant papers, analyze them, and use the available paper information to identify potential research directions.
Research Focus
The project is being developed with a particular interest in Generative AI and Retrieval-Augmented Generation (RAG) research.
Potential future research workflows include studying:
CRAG
Self-RAG
RAG evaluation
Retrieval quality
Hallucination reduction
Semantic retrieval
Conflicting evidence
Research-paper comparison
Literature-gap discovery
Current Status
π§ Active development
Current capabilities focus on:
Paper discovery β Paper analysis β Paper comparison β Research-gap exploration β Personal paper library
Future versions can extend this into deeper paper-level analysis, full-text research, retrieval over saved papers, and more advanced research workflows.
Author
Khushi Sonwane
Built as a hands-on project exploring Generative AI, MCP, academic research workflows, and RAG systems.
Available Tools
10 toolscompare_papersB
Compare multiple research papers.
Each paper should contain:
title
abstract
Inputs: papers (required). Returns: object
extract_limitationsA
Identify limitations and weaknesses mentioned or implied by the provided paper information.
Inputs: title (required), abstract (required). Returns: object
extract_methodologyC
Extract the methodology and technical approach from a paper.
Inputs: title (required), abstract (required). Returns: object
find_research_gapsC
Analyze multiple papers and identify potential research gaps.
Inputs: topic (required), papers (required). Returns: object
get_paperA
Retrieve detailed information about a specific arXiv paper.
Example: get_paper("2402.19473")
Inputs: arxiv_id (required). Returns: object
list_saved_papersB
Return all papers saved in the research library.
Inputs: no named parameters. Returns: object
save_paperC
Save a research paper to the local research library.
Inputs: paper (required). Returns: object
search_papersB
Search academic papers on arXiv.
Inputs: query (required), max_results. Returns: object
search_saved_papersC
Search through papers saved in the local research library.
Inputs: query (required). Returns: object
summarize_paperC
Generate a research-oriented summary of a paper.
The summary covers:
Problem
Approach
Results
Contribution
Inputs: title (required), abstract (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 10 tools
Each tool addresses a distinct research task: searching external papers, retrieving details, summarizing, comparing, extracting methodology, managing a personal library, identifying limitations, finding gaps, and saving papers. No two tools overlap in intent; even summarize_paper and extract_methodology focus on different aspects (overall summary vs. specific technical approach).
All tool names follow a consistent verb_noun pattern using snake_case (e.g., search_papers, get_paper, list_saved_papers, find_research_gaps). The verbs clearly describe the action and the nouns the target, making the naming predictable and easy to parse.
With 10 tools, the server is well-scoped for a research assistant. Each tool serves a necessary function in the search-analyze-save pipeline, and the count is neither sparse nor bloated, matching the domain scope appropriately.
The tool surface covers the core research workflow: search, retrieve, summarize, compare, extract methodology, identify limitations, find gaps, and manage a saved library. The only minor omission is a removal/delete operation for saved papers, but this does not create a dead end for typical use cases.
Maintenance
Related MCP Connectors
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Academic literature search, retrieval, and private library management on top of OpenAlex.
Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs wheβ¦
Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semanticβ¦
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered academic paper discovery, search, and analysis from arXiv with advanced features like semantic search, citation network analysis, and multi-format exports (BibTeX, RIS, JSON, CSV). Provides intelligent research assistance through specialized AI prompts for summarization, trend tracking, and literature review automation.17MIT
- FlicenseNot gradedqualityDmaintenanceEnables intelligent academic paper discovery through ArXiv search and AI-powered semantic similarity analysis. Helps researchers find and rank the most relevant papers using natural language queries and state-of-the-art sentence transformers.-
- AlicenseAqualityDmaintenanceEnables searching, downloading, and managing academic papers from arXiv.org through natural language interactions. Provides tools for paper discovery, PDF downloads, and local paper collection management.41MIT
- AlicenseNot gradedqualityDmaintenanceManages arXiv papers: search, download, analyze, and save AI-generated summaries. Enables AI assistants to interact with the arXiv platform.MIT