How to integrate Semanticscholar MCP with LangChain

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Semanticscholar Logo
LangChain Logo
divider

Introduction

This guide walks you through connecting Semanticscholar to LangChain using the Composio tool router. By the end, you'll have a working Semanticscholar agent that can find the latest papers on graph neural networks, list citations for a specific research paper, summarize an author’s recent publications, get references cited by a given paper through natural language commands.

This guide will help you understand how to give your LangChain agent real control over a Semanticscholar account through Composio's Semanticscholar MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Connect your Semanticscholar project to Composio
  • Create a Tool Router MCP session for Semanticscholar
  • Initialize an MCP client and retrieve Semanticscholar tools
  • Build a LangChain agent that can interact with Semanticscholar
  • Set up an interactive chat interface for testing

What is LangChain?

LangChain is a framework for developing applications powered by language models. It provides tools and abstractions for building agents that can reason, use tools, and maintain conversation context.

Key features include:

  • Agent Framework: Build agents that can use tools and make decisions
  • MCP Integration: Connect to external services through Model Context Protocol adapters
  • Memory Management: Maintain conversation history across interactions
  • Multi-Provider Support: Works with OpenAI, Anthropic, and other LLM providers

What is the Semanticscholar MCP server, and what's possible with it?

The Semanticscholar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Semantic Scholar account. It provides structured and secure access to scholarly data, so your agent can search for academic papers, retrieve detailed author profiles, analyze citations, and explore references or publication histories on your behalf.

  • Comprehensive literature search and discovery: Let your agent search for academic papers by topic, author, or relevance and retrieve lists of matching publications with rich metadata.
  • In-depth paper and author insights: Ask your agent to fetch detailed information about specific papers—including titles, abstracts, authors, and publication years—or get complete profiles for researchers and their entire body of work.
  • Citation and reference analysis: Enable your agent to trace the impact of a paper by pulling its citations or explore the foundational research it builds upon by listing its references.
  • Batch retrieval for large-scale research: Efficiently gather details on multiple papers or authors at once, streamlining reviews and bibliometric analyses across large datasets.
  • Bulk and relevance-based queries: Use advanced bulk search and filtering to identify up to thousands of papers at a time, making it easy for your agent to support systematic literature reviews and academic data exploration.

Supported Tools & Triggers

Tools
Details about an authorExamples: https://api.
Details about an author s papersRetrieves a list of papers authored by a specific researcher identified by their unique semantic scholar author id.
Details about a paperExamples: https://api.
Details about a paper s authorsRetrieves the list of authors for a specific paper identified by its unique paper id in the semantic scholar database.
Details about a paper s citationsRetrieves a list of citations for a specific academic paper using its unique semantic scholar paper id.
Details about a paper s referencesRetrieves the list of references cited by a specific paper in the semantic scholar database.
Get details for multiple authors at onceRetrieves detailed information for multiple authors from semantic scholar in a single api call.
Get details for multiple papers at onceThe semanticscholar paper batch endpoint allows users to retrieve data for multiple academic papers in a single api call.
Paper bulk searchBehaves similarly to /paper/search, but is intended for bulk retrieval of basic paper data without search relevance: text query is optional and supports boolean logic for document matching.
Paper relevance searchThe searchpapers endpoint allows users to search for academic papers within the semantic scholar database.
Paper title searchBehaves similarly to /paper/search, but is intended for retrieval of a single paper based on closest title match to given query.
Search for authors by nameThe authorsearch endpoint allows users to search for authors within the semantic scholar database.
Suggest paper query completionsTo support interactive query-completion, return minimal information about papers matching a partial query example: https://api.
Text snippet searchReturn the text snippets that most closely match the query.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting this tutorial, make sure you have:
  • Python 3.10 or higher installed on your system
  • A Composio account with an API key
  • An OpenAI API key
  • Basic familiarity with Python and async programming

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

pip install composio-langchain langchain-mcp-adapters langchain python-dotenv

Install the required packages for LangChain with MCP support.

What's happening:

  • composio-langchain provides Composio integration for LangChain
  • langchain-mcp-adapters enables MCP client connections
  • langchain is the core agent framework
  • python-dotenv loads environment variables

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_composio_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your requests to Composio's API
  • COMPOSIO_USER_ID identifies the user for session management
  • OPENAI_API_KEY enables access to OpenAI's language models

Import dependencies

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()
What's happening:
  • We're importing LangChain's MCP adapter and Composio SDK
  • The dotenv import loads environment variables from your .env file
  • This setup prepares the foundation for connecting LangChain with Semanticscholar functionality through MCP

Initialize Composio client

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))

    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
What's happening:
  • We're loading the COMPOSIO_API_KEY from environment variables and validating it exists
  • Creating a Composio instance that will manage our connection to Semanticscholar tools
  • Validating that COMPOSIO_USER_ID is also set before proceeding

Create a Tool Router session

# Create Tool Router session for Semanticscholar
session = composio.create(
    user_id=os.getenv("COMPOSIO_USER_ID"),
    toolkits=['semanticscholar']
)

url = session.mcp.url
What's happening:
  • We're creating a Tool Router session that gives your agent access to Semanticscholar tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
  • This approach allows the agent to dynamically load and use Semanticscholar tools as needed

Configure the agent with the MCP URL

client = MultiServerMCPClient({
    "semanticscholar-agent": {
        "transport": "streamable_http",
        "url": session.mcp.url,
        "headers": {
            "x-api-key": os.getenv("COMPOSIO_API_KEY")
        }
    }
})

tools = await client.get_tools()

agent = create_agent("gpt-5", tools)
What's happening:
  • We're creating a MultiServerMCPClient that connects to our Semanticscholar MCP server via HTTP
  • The client is configured with a name and the URL from our Tool Router session
  • get_tools() retrieves all available Semanticscholar tools that the agent can use
  • We're creating a LangChain agent using the GPT-5 model

Set up interactive chat interface

conversation_history = []

print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Semanticscholar related question or task to the agent.\n")

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ['exit', 'quit', 'bye']:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_history.append({"role": "user", "content": user_input})
    print("\nAgent is thinking...\n")

    response = await agent.ainvoke({"messages": conversation_history})
    conversation_history = response['messages']
    final_response = response['messages'][-1].content
    print(f"Agent: {final_response}\n")
What's happening:
  • We initialize an empty conversation_history list to maintain context across interactions
  • A while loop continuously accepts user input from the command line
  • When a user types a message, it's added to the conversation history and sent to the agent
  • The agent processes the request using the ainvoke() method with the full conversation history
  • Users can type 'exit', 'quit', or 'bye' to end the chat session gracefully

Run the application

if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • We call the main() function using asyncio.run() to start the application

Complete Code

Here's the complete code to get you started with Semanticscholar and LangChain:

from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent
from dotenv import load_dotenv
from composio import Composio
import asyncio
import os

load_dotenv()

async def main():
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    
    if not os.getenv("COMPOSIO_API_KEY"):
        raise ValueError("COMPOSIO_API_KEY is not set")
    if not os.getenv("COMPOSIO_USER_ID"):
        raise ValueError("COMPOSIO_USER_ID is not set")
    
    session = composio.create(
        user_id=os.getenv("COMPOSIO_USER_ID"),
        toolkits=['semanticscholar']
    )

    url = session.mcp.url
    
    client = MultiServerMCPClient({
        "semanticscholar-agent": {
            "transport": "streamable_http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    })
    
    tools = await client.get_tools()
  
    agent = create_agent("gpt-5", tools)
    
    conversation_history = []
    
    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Ask any Semanticscholar related question or task to the agent.\n")
    
    while True:
        user_input = input("You: ").strip()
        
        if user_input.lower() in ['exit', 'quit', 'bye']:
            print("\nGoodbye!")
            break
        
        if not user_input:
            continue
        
        conversation_history.append({"role": "user", "content": user_input})
        print("\nAgent is thinking...\n")
        
        response = await agent.ainvoke({"messages": conversation_history})
        conversation_history = response['messages']
        final_response = response['messages'][-1].content
        print(f"Agent: {final_response}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've successfully built a LangChain agent that can interact with Semanticscholar through Composio's Tool Router.

Key features of this implementation:

  • Dynamic tool loading through Composio's Tool Router
  • Conversation history maintenance for context-aware responses
  • Async Python provides clean, efficient execution of agent workflows
You can extend this further by adding error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

How to build Semanticscholar MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Semanticscholar MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Semanticscholar MCP with Claude Agent SDK

Google ADK

Google ADK

Use Semanticscholar MCP with Google ADK

Vercel AI SDK

Vercel AI SDK

Use Semanticscholar MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Semanticscholar MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Semanticscholar MCP with LlamaIndex

CrewAI

CrewAI

Use Semanticscholar MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Semanticscholar MCP?

With a standalone Semanticscholar MCP server, the agents and LLMs can only access a fixed set of Semanticscholar tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Semanticscholar and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LangChain?

Yes, you can. LangChain fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Semanticscholar tools.

Can I manage the permissions and scopes for Semanticscholar while using Tool Router?

Yes, absolutely. You can configure which Semanticscholar scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Semanticscholar data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free