Vercel 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. Set up the connector

   Register your Vercel MCP credentials with Scalekit so it handles the token lifecycle. You do this once per environment.

   Dashboard setup steps

   Register your Firecrawl API key with Scalekit so it can authenticate and proxy scraping requests on behalf of your users. Vercel MCP uses API key authentication — there is no redirect URI or OAuth flow.

   1. Get a Firecrawl API key

      • Go to firecrawl.dev and sign in or create a free account.
      • Your API key is shown on the Overview page under API Key. Copy it — it starts with fc-.

   2. Create a connection in Scalekit

      • In the Scalekit dashboard, go to AgentKit → Connections → Create Connection.
      • Search for Vercel MCP and click Create.
      • Note the Connection name — use this as connection_name in your code (e.g., vercelmcp).

   3. Add a connected account

      Connected accounts link a specific user identifier in your system to a Firecrawl API key. Add them via the dashboard for testing, or via the Scalekit API in production.

      Via dashboard (for testing)

      • Open the connection and click the Connected Accounts tab → Add account.
      • Fill in Your User’s ID and API Key, then click Save.

      Via API (for production)

      Node.js

      await scalekit.actions.upsertConnectedAccount({
        connectionName: 'vercelmcp',
        identifier: 'user_123',
        credentials: { token: 'fc-...' },
      });

      Python

      scalekit_client.actions.upsert_connected_account(
          connection_name="vercelmcp",
          identifier="user_123",
          credentials={"token": "fc-..."}
      )

4. 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 = 'vercelmcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Vercel 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: 'vercelmcp_deploytovercel',
     toolInput: {},
   })
   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 = "vercelmcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Vercel MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="vercelmcp_deploytovercel",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Addtoolbarreaction records — Add an emoji reaction to a message in a toolbar thread
• Changetoolbarthreadresolvestatus records — Change the resolve status of a toolbar thread
• Checkdomainavailabilityandprice records — Check if domain names are available for purchase and get pricing information
• Deploytovercel records — Deploy the current project to Vercel
• Edittoolbarmessage records — Edit an existing message in a toolbar thread
• Getaccesstovercelurl records — Creates a temporary shareable link that bypasses authentication for a Vercel deployment URL

Common workflows

Scrape a page

Use vercelmcp_firecrawl_scrape to extract clean markdown content from any URL.

Node.js

const result = await actions.executeTool({
  connectionName: 'vercelmcp',
  identifier: 'user_123',
  toolName: 'vercelmcp_firecrawl_scrape',
  toolInput: {
    url: 'https://docs.example.com/getting-started',
    onlyMainContent: true,
  },
});
console.log(result.data);

Python

result = actions.execute_tool(
    connection_name="vercelmcp",
    identifier="user_123",
    tool_name="vercelmcp_firecrawl_scrape",
    tool_input={
        "url": "https://docs.example.com/getting-started",
        "onlyMainContent": True,
    },
)
print(result.data)

Search the web

Use vercelmcp_firecrawl_search to run a live web search and get scraped content from the top results.

Node.js

const result = await actions.executeTool({
  connectionName: 'vercelmcp',
  identifier: 'user_123',
  toolName: 'vercelmcp_firecrawl_search',
  toolInput: {
    query: 'best practices for API rate limiting 2026',
    limit: 5,
  },
});
console.log(result.data);

Python

result = actions.execute_tool(
    connection_name="vercelmcp",
    identifier="user_123",
    tool_name="vercelmcp_firecrawl_search",
    tool_input={
        "query": "best practices for API rate limiting 2026",
        "limit": 5,
    },
)
print(result.data)

Extract structured data from a URL

Use vercelmcp_firecrawl_extract with a natural-language prompt and optional JSON Schema to pull structured data from one or more pages.

Node.js

const result = await actions.executeTool({
  connectionName: 'vercelmcp',
  identifier: 'user_123',
  toolName: 'vercelmcp_firecrawl_extract',
  toolInput: {
    urls: ['https://example.com/pricing'],
    prompt: 'Extract all pricing plan names and their monthly costs.',
  },
});
console.log(result.data);

Python

result = actions.execute_tool(
    connection_name="vercelmcp",
    identifier="user_123",
    tool_name="vercelmcp_firecrawl_extract",
    tool_input={
        "urls": ["https://example.com/pricing"],
        "prompt": "Extract all pricing plan names and their monthly costs.",
    },
)
print(result.data)

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.

vercelmcp_addtoolbarreaction # Add an emoji reaction to a message in a toolbar thread 4 params ▾

Add an emoji reaction to a message in a toolbar thread

Name Type Required Description

emoji string required The emoji character to use as the reaction (e.g. '👍', '❤️')

messageId string required The ID of the message to react to

teamId string required The ID of the team that owns the thread

threadId string required The ID of the toolbar thread containing the message

vercelmcp_changetoolbarthreadresolvestatus # Change the resolve status of a toolbar thread 3 params ▾

Change the resolve status of a toolbar thread

Name Type Required Description

resolved boolean required Set to true to mark the thread as resolved, false to mark it as unresolved

teamId string required The ID of the team that owns the thread

threadId string required The ID of the toolbar thread to update

vercelmcp_checkdomainavailabilityandprice # Check if domain names are available for purchase and get pricing information 1 param ▾

Check if domain names are available for purchase and get pricing information

Name Type Required Description

names array required List of domain names to check for availability and pricing

vercelmcp_deploytovercel # Deploy the current project to Vercel 0 params ▾

Deploy the current project to Vercel

vercelmcp_edittoolbarmessage # Edit an existing message in a toolbar thread 4 params ▾

Edit an existing message in a toolbar thread

Name Type Required Description

markdown string required The updated message content in Markdown format

messageId string required The ID of the message to edit

teamId string required The ID of the team that owns the thread

threadId string required The ID of the toolbar thread containing the message

vercelmcp_getaccesstovercelurl # Creates a temporary shareable link that bypasses authentication for a Vercel deployment URL 1 param ▾

Creates a temporary shareable link that bypasses authentication for a Vercel deployment URL

Name Type Required Description

url string required The Vercel deployment URL to create a temporary shareable access link for

vercelmcp_getdeployment # Get a specific deployment by ID or URL 2 params ▾

Get a specific deployment by ID or URL

Name Type Required Description

idOrUrl string required The deployment ID or URL to retrieve

teamId string required The ID of the team that owns the deployment

vercelmcp_getdeploymentbuildlogs # Get the build logs of a deployment by deployment ID or URL 2 params ▾

Get the build logs of a deployment by deployment ID or URL

Name Type Required Description

idOrUrl string required The deployment ID or URL whose build logs to retrieve

teamId string required The ID of the team that owns the deployment

vercelmcp_getproject # Get a specific project in Vercel 2 params ▾

Get a specific project in Vercel

Name Type Required Description

projectId string required The ID of the project to retrieve

teamId string required The ID of the team that owns the project

vercelmcp_getruntimelogs # Get runtime logs for a project or deployment 4 params ▾

Get runtime logs for a project or deployment

Name Type Required Description

projectId string required The ID of the project whose runtime logs to retrieve

teamId string required The ID of the team that owns the project

deploymentId string optional Optional deployment ID to filter runtime logs to a specific deployment

limit number optional Maximum number of log entries to return

vercelmcp_gettoolbarthread # Get a specific toolbar thread by ID 2 params ▾

Get a specific toolbar thread by ID

Name Type Required Description

teamId string required The ID of the team that owns the thread

threadId string required The ID of the toolbar thread to retrieve

vercelmcp_importclaudedesignfromurl # Import a design into Vercel from a publicly fetchable URL 3 params ▾

Import a design into Vercel from a publicly fetchable URL

Name Type Required Description

teamId string required The ID of the team to import the design into

url string required The publicly fetchable URL of the design to import

projectId string optional The ID of the project to associate the design with (optional)

vercelmcp_listdeployments # List all deployments for a project 4 params ▾

List all deployments for a project

Name Type Required Description

projectId string required The ID of the project whose deployments to list

teamId string required The ID of the team that owns the project

limit number optional Maximum number of deployments to return

state string optional Filter deployments by state (e.g. READY, ERROR, BUILDING, QUEUED, CANCELED)

vercelmcp_listprojects # List all Vercel projects for a user (with a max of 50) 3 params ▾

List all Vercel projects for a user (with a max of 50)

Name Type Required Description

teamId string required The ID of the team whose projects to list

limit number optional Maximum number of projects to return (max 50)

search string optional Search query to filter projects by name

vercelmcp_listteams # List the user's teams 0 params ▾

List the user's teams

vercelmcp_listtoolbarthreads # List Vercel toolbar comment threads for a team 3 params ▾

List Vercel toolbar comment threads for a team

Name Type Required Description

teamId string required The ID of the team whose toolbar threads to list

deploymentId string optional Filter threads by deployment ID (optional)

projectId string optional Filter threads by project ID (optional)

vercelmcp_replytotoolbarthread # Add a reply message to an existing toolbar thread 3 params ▾

Add a reply message to an existing toolbar thread

Name Type Required Description

markdown string required The reply message content in Markdown format

teamId string required The ID of the team that owns the thread

threadId string required The ID of the toolbar thread to reply to

vercelmcp_searchverceldocumentation # Search the Vercel documentation for information about a topic 2 params ▾

Search the Vercel documentation for information about a topic

Name Type Required Description

topic string required The topic or query to search for in the Vercel documentation

limit number optional Maximum number of documentation results to return

vercelmcp_webfetchvercelurl # Fetches a Vercel deployment URL and returns the response body 1 param ▾

Fetches a Vercel deployment URL and returns the response body

Name Type Required Description

url string required The Vercel deployment URL to fetch