Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the Scholar Gateway MCP server

Vendor MCP
Open markdown

The Scholar Gateway MCP connector routes your AI agent's tool calls to Scholar Gateway's own MCP server through Scalekit. Each user signs in to Scholar Gateway once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 1 tool.

Tools
1
What they doRead · write · destructive
1 · 0 · 01 read0 write0 destructive
Users sign in with
OAuth app
Scalekit's or your own

What you can do

  • Search academic literature: find relevant passages in full-text academic publications with citation details, filtered by publication year

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Create the Scholar Gateway MCP connection

    In AgentKit > Connections, create a Scholar Gateway MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

    Scalekit credentials are available for Scholar Gateway MCP server, so you don't need to register an OAuth app.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'scholargateway'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Scholar Gateway MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'scholargateway_semanticSearch',
      toolInput: { query: 'YOUR_QUERY' },
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • scholargateway_semanticSearchSearches a full-text academic corpus and returns relevant passages with citation metadata.Read-only

    Semantic Search

    Searches a full-text academic corpus and returns relevant passages with citation metadata. When to use: Use this tool for research questions, factual claims, literature-backed explanations, evidence-based summaries, and any response where academic support would improve accuracy, credibility, or depth. Submit queries as complete natural language questions — preserve the full intent and do not reduce to keywords. For ambiguous or polysemous terms, expand to full context before searching (e.g. use 'multiple sclerosis' not 'MS'). Cite all substantive claims inline using author-year format with DOI hyperlinks. When NOT to use: Do not use for general web searches, non-academic topics, or when the question requires real-time or proprietary data not covered by the academic corpus.

    Inputs

    querystringrequired
    Natural language research question. Preserve intent, scope, and structure. Rewrite for semantic clarity but do not compress to keywords. Expand acronyms and add field context for ambiguous or polysemous terms.
    end_yearstring
    Inclusive upper bound for publication year filter. Omit to include publications up to the present.
    includeRetractedContentboolean
    Whether to include retracted publications in results. Default false; set true only when retraction history is itself the subject of inquiry.default false
    start_yearstring
    Inclusive lower bound for publication year filter. Omit to search across all available years.
    topNinteger
    Number of passages to return. Higher values improve recall for broad or multi-faceted queries; lower values are appropriate for narrow or well-defined topics.default 15
All 116 in AI