AlphaXiv MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

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. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'alphaxivmcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize AlphaXiv MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'alphaxivmcp_get_paper_content',
     toolInput: { url: 'https://example.com/url' },
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "alphaxivmcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize AlphaXiv MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={"url":"https://example.com/url"},
       tool_name="alphaxivmcp_get_paper_content",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Read files from github repository — Reads the contents of a file or directory from the paper’s codebase repository
• Get paper content — Get the content of an arXiv/alphaXiv paper as text
• Papers discover — Discovers and ranks multiple candidate papers for a research topic
• Queries answer pdf — Returns raw filtered page content from one PDF as XML

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

alphaxivmcp_answer_pdf_queries#Returns raw filtered page content from one PDF as XML. Supports arXiv, alphaXiv, and Semantic Scholar abstract pages. Multiple queries on the same paper can be batched into one call.2 params▾

Returns raw filtered page content from one PDF as XML. Supports arXiv, alphaXiv, and Semantic Scholar abstract pages. Multiple queries on the same paper can be batched into one call.

NameTypeRequiredDescription

queriesarrayrequiredA brief description of what information you're looking for in the paper.

urlstringrequiredA PDF URL (e.g., 'https://arxiv.org/pdf/2307.12307', 'https://alphaxiv.org/abs/2307.12307')

alphaxivmcp_discover_papers#Discovers and ranks multiple candidate papers for a research topic. Use for literature discovery, related work, or broad topical coverage.3 params▾

Discovers and ranks multiple candidate papers for a research topic. Use for literature discovery, related work, or broad topical coverage.

NameTypeRequiredDescription

difficultynumberrequiredA 1-10 estimate of how much retrieval effort this request warrants.

keywordsarrayrequired3-4 concise keyword terms for exact-name, acronym, method, benchmark, author, or title matching.

questionstringrequiredA detailed semantic description of the papers that would best answer the user's request.

alphaxivmcp_get_paper_content#Get the content of an arXiv/alphaXiv paper as text. By default returns a structured AI-generated intermediate report. Use the fullText option to get raw extracted text.2 params▾

Get the content of an arXiv/alphaXiv paper as text. By default returns a structured AI-generated intermediate report. Use the fullText option to get raw extracted text.

NameTypeRequiredDescription

urlstringrequiredAn arXiv or alphaXiv URL

fullTextbooleanoptionalIf true, return the full extracted text instead of the intermediate report.

alphaxivmcp_read_files_from_github_repository#Reads the contents of a file or directory from the paper's codebase repository. Returns repository structure for '/', directory listing for directories, or file contents for files.2 params▾

Reads the contents of a file or directory from the paper's codebase repository. Returns repository structure for '/', directory listing for directories, or file contents for files.

NameTypeRequiredDescription

githubUrlstringrequiredThe URL of the paper's codebase repository.

pathstringrequiredThe path to the file or directory. Use '/' to get the entire repository structure.