SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Semanticscholar MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Semanticscholar MCP. Find the latest papers on graph neural networks, list citations for a specific research paper, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Semanticscholar logoSemanticscholar
Api Key

Semantic Scholar is an AI-powered academic search engine for scientific literature. It helps researchers quickly discover, analyze, and understand research papers across disciplines.

20 Tools

Introduction

This guide walks you through connecting Semanticscholar to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Semanticscholar agent that can search papers by title or relevance, look up authors, trace citations and references, find paper recommendations, and search text snippets through natural language commands.

This guide will help you understand how to give your Vercel AI SDK 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.

Also integrate Semanticscholar with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKMuseCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Semanticscholar integration
  • Using Composio's Tool Router to dynamically load and access Semanticscholar tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

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

The Semantic Scholar 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 academic papers, author profiles, citations, recommendations, and dataset releases, so your agent can search literature, examine research, explore authors, find related papers, and retrieve dataset information on your behalf.

  • Academic paper discovery: Have your agent search papers by relevance, run bulk literature searches, find a paper by title, complete partial queries, or locate matching text snippets within papers.
  • Paper details and authorship: Let the agent retrieve details about one or more papers, identify their authors, and review key information about each work.
  • Citations and references: Direct your agent to inspect the papers that cite a study and the references used by that study.
  • Author research: Instruct your agent to search for researchers by name, review author profiles and publication statistics, or examine papers written by selected authors.
  • Recommendations and research datasets: Have your agent find related papers from positive and negative examples, list dataset releases, review release details, and retrieve dataset downloads or incremental updates.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["semanticscholar"],
  });

  const mcpUrl = 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 mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Semanticscholar-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Semanticscholar tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to semanticscholar, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Semanticscholar tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Semanticscholar and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["semanticscholar"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to semanticscholar, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Semanticscholar agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Semanticscholar action and event your agent gets out of the box.

Details about an author

Retrieve detailed information about an author from Semantic Scholar, including name, affiliations, publication statistics (paperCount, citationCount, h-index), external IDs (ORCID, DBLP), and optionally papers.

Details about an author s papers

Retrieves a list of papers authored or co-authored by a specific researcher identified by their unique Semantic Scholar author ID.

Details about a paper

Retrieve details for a paper by its ID, with selectable fields.

Details about a paper s authors

Retrieve a paginated list of authors for a Semantic Scholar paper, identified by a supported ID such as a Semantic Scholar ID, DOI, or arXiv ID.

Details about a paper s citations

Retrieve a paginated list of papers citing a specified paper.

Details about a paper s references

Retrieves the list of references cited by a specific paper in the Semantic Scholar database.

Get dataset download links

Tool to get download links for a specific dataset within a release.

Get dataset diffs

Get download links for incremental diffs between dataset releases.

Get details for multiple authors at once

Retrieve details for up to 1,000 Semantic Scholar authors by ID in one batch, with selectable author and paper fields.

Get details for multiple papers at once

Retrieve detailed information for multiple academic papers in a single API call using the Semantic Scholar paper batch endpoint.

Get paper recommendations

Tool to get paper recommendations based on positive and negative example papers.

Get recommendations for paper

Tool to get recommended papers for a single positive example paper.

Get dataset release information

Tool to retrieve metadata for a specific Semantic Scholar dataset release.

List available dataset releases

Tool to list all available dataset releases from Semantic Scholar.

Paper title search

Behaves similarly to /paper/search, but is intended for retrieval of a single paper based on closest title match to given query.

Search Bulk Papers

Tool to perform bulk search for academic papers.

Search for authors by name

Search for academic authors in the Semantic Scholar database by name.

Search papers by relevance

Tool to search for academic papers by relevance in the Semantic Scholar database.

Suggest paper query completions

Get autocomplete suggestions for paper queries.

Text snippet search

Search for text snippets matching a plain-text query in academic papers.

FRAMEWORKS

How to build Semanticscholar MCP Agent with another framework

Claude Code logo

Claude Code

Use Semanticscholar MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Semanticscholar MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Semanticscholar MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Semanticscholar MCP with Claude Agent SDK

Muse logo

Muse

Use Semanticscholar MCP with Muse

Codex logo

Codex

Use Semanticscholar MCP with Codex

OpenClaw logo

OpenClaw

Use Semanticscholar MCP with OpenClaw

Hermes logo

Hermes

Use Semanticscholar MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Semanticscholar MCP with Atomic Agent

Google ADK logo

Google ADK

Use Semanticscholar MCP with Google ADK

LangChain logo

LangChain

Use Semanticscholar MCP with LangChain

Mastra AI logo

Mastra AI

Use Semanticscholar MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Semanticscholar MCP with LlamaIndex

CrewAI logo

CrewAI

Use Semanticscholar MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Semanticscholar MCP with Pydantic AI

AutoGen logo

AutoGen

Use Semanticscholar MCP with AutoGen

FAQ

Frequently asked questions

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.

Yes, you can. Vercel AI SDK v6 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.

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.

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.

Start with Semanticscholar.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Semanticscholar tool your agent needs.Free to start.

Start building