Graphify MCP for Vercel

Graphify for Vercel connects Vercel projects to Graphify’s hosted MCP server. Your app or agent can query indexed repositories for definitions, callers, dependencies, change impact, and repository knowledge with source references. There are two Vercel paths:

Marketplace integration: a Graphify workspace owner or admin connects an existing workspace to selected Vercel projects. Each selected project receives GRAPHIFY_MCP_URL and a sensitive GRAPHIFY_MCP_TOKEN. Use this when one Vercel project should call Graphify as that workspace.
Vercel Connect connector: each person using your app authorizes their own Graphify account. Your app asks @vercel/connect for a token for that person. Use this when the app should call Graphify as the signed-in user.

Both paths call the same hosted server used by Graphify MCP for VS Code, Graphify MCP for JetBrains, Graphify for ChatGPT, and Graphify MCP for OpenClaw.

Marketplace integration

Use the Marketplace integration when a Vercel project needs a project-scoped MCP token managed from Vercel.

Before you start

You are a Graphify workspace owner or admin.
You have a repository indexed in Graphify, with agent access enabled.
You can select the Vercel projects and deployment environments that should receive Graphify MCP credentials.
You will keep the credentials in server-side code. Do not expose GRAPHIFY_MCP_TOKEN to browser code.

Your Graphify plan, usage limits, and billing stay with Graphify. See pricing.

1. Install from Vercel Marketplace

Open Graphify for Vercel.
Select Connect Account.
Authorize the existing Graphify workspace.
Select the Vercel projects that should receive Graphify MCP access.
Choose deployment environments. Production is selected by default; preview access is optional.

The integration adds two variables to each chosen project:

Variable	Purpose
`GRAPHIFY_MCP_URL`	The hosted Graphify MCP endpoint for the project.
`GRAPHIFY_MCP_TOKEN`	A sensitive project token for that Vercel project.

Redeploy the selected projects so the new variables are available at runtime. For local development, pull project environment variables with the Vercel workflow you already use. Server-side code sends GRAPHIFY_MCP_TOKEN to the Graphify MCP server as a Bearer token. Use the GRAPHIFY_MCP_URL value from the project environment instead of hard-coding the endpoint.

2. Call Graphify from eve

eve is Vercel’s agent project. Put the connection in agent/connections/graphify.ts:

import { defineMcpClientConnection } from 'eve/connections'

const graphifyMcpUrl = process.env.GRAPHIFY_MCP_URL
const graphifyMcpToken = process.env.GRAPHIFY_MCP_TOKEN

if (!graphifyMcpUrl || !graphifyMcpToken) {
  throw new Error('Graphify MCP environment variables are missing')
}

export default defineMcpClientConnection({
  url: graphifyMcpUrl,
  description: 'Graphify code graph: definitions, callers, dependencies, impact, and repository knowledge.',
  auth: {
    credentialOwner: 'app',
    getToken: async () => ({ token: graphifyMcpToken }),
  },
})

eve keeps the credential out of the model. Its static-token auth sends the token as a Bearer token when it connects to the MCP server.

3. Call Graphify from the AI SDK

The AI SDK can load tools from Graphify’s MCP server and pass them to a model. This sample reads the Marketplace variables from server-side code:

import { createMCPClient } from '@ai-sdk/mcp'
import { generateText, isStepCount } from 'ai'

const graphifyMcpUrl = process.env.GRAPHIFY_MCP_URL
const graphifyMcpToken = process.env.GRAPHIFY_MCP_TOKEN

if (!graphifyMcpUrl || !graphifyMcpToken) {
  throw new Error('Graphify MCP environment variables are missing')
}

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: graphifyMcpUrl,
    headers: { Authorization: `Bearer ${graphifyMcpToken}` },
  },
})

try {
  const { text } = await generateText({
    model: 'openai/gpt-5.4',
    tools: await client.tools(),
    stopWhen: isStepCount(10),
    prompt: 'Use Graphify to help with this request.',
  })
} finally {
  await client.close()
}

The model id above is the Vercel listing’s sample. Graphify does not choose the model for your app.

4. Manage the integration

Use Configure in Vercel to manage the Graphify connection.

Disconnecting a project revokes that project’s token.
Removing the integration revokes every token from that installation.
Your Graphify account and subscription stay intact after removal.

Vercel Connect connector

Use Vercel Connect when each person using the app should authorize their own Graphify account. Connect gives your app a token for that person. The app sends that token to Graphify. acme-graphify below is the example name from the Connect listing. Pick your own. The token id is graphify/ plus that name.

Before you start

A Vercel account and the Vercel CLI. Connect is available on all Vercel plans. See Vercel Connect.
A Vercel project. vercel link attaches this directory to it. The project can be empty. It exists so Vercel can issue a token to your code.
A repository indexed in your Graphify workspace. Sign in at app.graphify.com, connect a repository, and wait until its status is Indexed. See Repositories and builds.

If a coding agent is writing this Vercel app, the Connect listing’s first command installs Vercel’s Connect skill:

npx skills add vercel/vercel-plugin --skill vercel-connect

That skill is Vercel’s. It is separate from graphify install.

1. Create the connector

Open Graphify on Vercel Connect and choose Create Connector, or run this from the project directory:

vercel link
vercel connect create graphify --name acme-graphify
vercel env pull

vercel env pull writes a local VERCEL_OIDC_TOKEN so getToken can run on your machine. On a Vercel deployment, Vercel supplies that token. If a later call cannot authenticate, run vercel env pull again. The local token is short-lived. Details are in the Connect quickstart. Complete the Graphify authorization Vercel shows. The listing requests access for the person using the app, under that person’s Graphify permissions.

2. Ask Connect for a token

@vercel/connect is the Connect SDK. Install it, then call getToken with the id of the person using your app. user_123 below is a placeholder.

npm install @vercel/connect

import { getToken } from '@vercel/connect'

const userId = 'user_123'

const token = await getToken('graphify/acme-graphify', {
  subject: { type: 'user', id: userId },
})

Send token to https://api.graphify.com/mcp as Authorization: Bearer <token>. The eve and AI SDK sections below do that for you.

3. Call Graphify

Use one of the two stacks from the listing, or send the Bearer token from your own route.

eve

eve is Vercel’s agent project. You declare Graphify as a connection, and eve attaches the tools.

npx eve@latest init my-agent
cd my-agent
npm install @vercel/connect
vercel link
vercel connect create graphify --name acme-graphify
vercel env pull

Add agent/connections/graphify.ts:

import { defineMcpClientConnection } from 'eve/connections'
import { connect } from '@vercel/connect/eve'

export default defineMcpClientConnection({
  url: 'https://api.graphify.com/mcp',
  description: 'Graphify tools and data',
  auth: connect('graphify/acme-graphify'),
})

npm run dev

AI SDK

The AI SDK is Vercel’s library for calling a model from your code and handing it tools. This sample is the one on the listing, including the model id.

npm install ai @ai-sdk/mcp @vercel/connect
vercel link
vercel connect create graphify --name acme-graphify
vercel env pull

import { getToken } from '@vercel/connect'
import { createMCPClient } from '@ai-sdk/mcp'
import { generateText, isStepCount } from 'ai'

const userId = 'user_123'
const token = await getToken('graphify/acme-graphify', {
  subject: { type: 'user', id: userId },
})

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: 'https://api.graphify.com/mcp',
    headers: { Authorization: `Bearer ${token}` },
  },
})

try {
  const { text } = await generateText({
    model: 'openai/gpt-5.4',
    tools: await client.tools(),
    stopWhen: isStepCount(10),
    prompt: 'Use Graphify to help with this request.',
  })
} finally {
  await client.close()
}

If something fails

What you see	What to do
Marketplace variables are missing	Confirm the project was selected during install, redeploy the project, and pull environment variables for local development.
The Marketplace token is rejected	Check that the project is still connected in Vercel, the app was redeployed after install, and server-side code sends `GRAPHIFY_MCP_TOKEN` as the Bearer token.
`getToken` cannot authenticate	Run `vercel env pull` again from the linked project. The local OIDC token expires. A deployment on Vercel receives its own token.
The Connect token id is rejected	The id is `graphify/` plus the `--name` you passed to `vercel connect create`. `graphify/acme-graphify` matches the example name only.
No repositories, or empty answers	That repository is not indexed yet, or it is in a different workspace. Check its status in Repositories and builds.
The tools are the ten local ones	This page uses the hosted server. The ten-tool list in the MCP tool reference is the graph on the machine.

Graphify MCP for VS Code

Connect an editor to the same hosted server.

Vercel Connect

How Connect issues a token and how a project is allowed to ask for one.

​Marketplace integration

​Before you start

​1. Install from Vercel Marketplace

​2. Call Graphify from eve

​3. Call Graphify from the AI SDK

​4. Manage the integration

​Vercel Connect connector

​Before you start

​1. Create the connector

​2. Ask Connect for a token

​3. Call Graphify

​eve

​AI SDK

​If something fails

​Related

Graphify MCP for VS Code

Vercel Connect

Marketplace integration

Before you start

1. Install from Vercel Marketplace

2. Call Graphify from eve

3. Call Graphify from the AI SDK

4. Manage the integration

Vercel Connect connector

Before you start

1. Create the connector

2. Ask Connect for a token

3. Call Graphify

eve

AI SDK

If something fails

Related