Merge Unified's Vercel integration Merge Agent Handler's Vercel MCP server

Connect your AI Agents to Vercel in minutes

Merge lets you securely connect your agents to Vercel and thousands of tools instantly

Start building for free

Read docs

Vercel

Learn more about Merge Agent Handler

Available tools

list_deployments

List Vercel deployments with pagination. Filter by project, target, or state. Use 'until' cursor from page_info for next page.

create_deployment

Create a new Vercel deployment. Provide project name and optionally a Git source or files to deploy. Use list_projects to find valid project names.

get_deployment

Get a Vercel deployment by ID or URL. Returns deployment details including state, URL, and metadata. Use list_deployments to find valid IDs.

delete_deployment

Delete a Vercel deployment by ID. This permanently removes the deployment. Use list_deployments to find valid IDs.

cancel_deployment

Cancel an in-progress Vercel deployment. Only works on deployments that are currently building. Use list_deployments to find valid IDs.

list_deployment_files

List files in a Vercel deployment. Returns the file tree of the deployed output. Use list_deployments to find valid deployment IDs.

get_deployment_events

Get build logs and events for a Vercel deployment. Returns build output and status changes. Use list_deployments to find valid IDs.

list_domains

List all domains on the Vercel account with pagination. Use 'until' cursor from page_info for next page.

get_domain

Get details for a specific domain including verification and configuration status. Use list_domains to find valid domain names.

add_domain

Add a domain to your Vercel account. After adding, configure DNS to point to Vercel. Use getdomainconfig to check DNS status.

update_domain

Update or move a domain. Use op='move' with destination team ID to transfer a domain between teams. Use list_domains to find valid names.

delete_domain

Remove a domain from your Vercel account. This does not affect DNS records. Use list_domains to find valid domain names.

get_domain_config

Get DNS configuration status for a domain. Shows whether the domain is properly configured and any required DNS changes.

list_env_vars

List environment variables for a Vercel project. Values may be encrypted. Use getenvvar to decrypt. Use 'until' cursor from page_info for next page.

create_env_var

Create an environment variable for a Vercel project. Specify key, value, type (plain/encrypted/secret/sensitive), and target environments.

get_env_var

Get a decrypted environment variable value by ID. Use listenvvars to find valid env var IDs for the project.

update_env_var

Update an environment variable's key, value, type, or target environments. Use listenvvars to find valid env var IDs.

delete_env_var

Delete an environment variable from a Vercel project. Use listenvvars to find valid env var IDs.

delete_env_vars_batch

Batch delete multiple environment variables from a Vercel project. Use listenvvars to find valid env var IDs.

list_feature_flags

List feature flags for a Vercel project. Supports filtering by state and search. Use cursor from page_info for next page.

get_feature_flag

Get details of a specific feature flag by ID. Use listfeatureflags to find valid flag IDs.

list_feature_flag_segments

List feature flag segments for a Vercel project. Segments define user groups for targeting.

get_feature_flag_segment

Get details of a specific feature flag segment by ID. Use listfeatureflag_segments to find valid segment IDs.

list_projects

List Vercel projects with pagination. Use 'until' cursor from page_info for next page. Optionally filter by search term.

create_project

Create a new Vercel project. Optionally connect a Git repository and set framework, build command, and environment variables.

get_project

Get a Vercel project by ID or name. Returns project details including framework, Git repo, and settings. Use list_projects to find valid IDs.

update_project

Update a Vercel project's settings such as name, framework, build command, or output directory. Use list_projects to find valid IDs.

delete_project

Delete a Vercel project by ID or name. This permanently removes the project and all its deployments. Use list_projects to find valid IDs.

list_project_domains

List domains assigned to a Vercel project. Use 'until' cursor from pageinfo for next page. Use listprojects to find valid project IDs.

add_project_domain

Add a domain to a Vercel project. Optionally configure redirect or link to a git branch. Use list_projects to find valid project IDs.

remove_project_domain

Remove a domain from a Vercel project. Use listprojectdomains to find valid domain names for the project.

pause_project

Pause a Vercel project. Paused projects stop serving traffic. Use list_projects to find valid project IDs.

unpause_project

Unpause a Vercel project. Resumes traffic to the project's deployments. Use list_projects to find valid project IDs.

list_shared_env_vars

List shared (team-level) environment variables. These are shared across all projects in the team. Use list_teams to find valid team IDs.

create_shared_env_var

Create a shared (team-level) environment variable. Shared vars are accessible to all projects in the team. Use list_teams to find valid team IDs.

get_shared_env_var

Get a decrypted shared environment variable by ID. Use listsharedenv_vars to find valid IDs.

update_shared_env_var

Update a shared environment variable's key, value, type, or target. Use listsharedenv_vars to find valid IDs.

delete_shared_env_vars

Delete one or more shared environment variables by ID. Use listsharedenv_vars to find valid IDs.

disconnect_shared_env_var

Disconnect a shared environment variable from a specific project. The variable remains but is no longer linked to the project.

list_teams

List all Vercel teams the authenticated user belongs to. Use 'until' cursor from page_info for next page.

get_team

Get details for a Vercel team by ID including name, slug, and membership info. Use list_teams to find valid team IDs.

create_team

Create a new Vercel team. Requires a unique URL slug. Optionally set a display name.

update_team

Update a Vercel team's name, slug, or description. Use list_teams to find valid team IDs.

delete_team

Delete a Vercel team. This permanently removes the team and all associated resources. Use list_teams to find valid team IDs.

list_team_members

List members of a Vercel team with pagination. Use 'until' cursor from pageinfo for next page. Use listteams to find valid team IDs.

invite_team_member

Invite a user to a Vercel team by email. Assign a role: MEMBER, OWNER, VIEWER, DEVELOPER, or BILLING. Use list_teams to find valid team IDs.

get_authenticated_user

Get the currently authenticated Vercel user's profile including email, username, and avatar.

list_user_events

List activity events for the authenticated user. Shows recent actions like deployments, domain changes, and team activity. Use 'until' cursor for next page.

validate_credential

Validate Vercel credentials. Verifies credentials during setup.

list_webhooks

List all webhooks configured for the account or team. Returns webhook IDs, URLs, and subscribed events.

create_webhook

Create a webhook to receive event notifications. Specify URL and event types (e.g. deployment.created, project.created).

get_webhook

Get details of a specific webhook by ID. Use list_webhooks to find valid webhook IDs.

delete_webhook

Delete a webhook by ID. Use list_webhooks to find valid webhook IDs.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}

Copy Code

FAQs on using Merge's Vercel MCP server

What is a Vercel MCP?

It's an MCP server that lets your agents access data and functionality from Vercel via tools. Your agents can invoke these tools to trigger deployments, manage environment variables, configure domains, monitor deployment events, and more.

Vercel offers an official MCP server, but you can use one from a third-party platform, like Merge Agent Handler.

How can I use the Vercel MCP server?

The use cases naturally depend on the agent you've built, but here are a few common ones:

Automated deployment on merge: When a pull request is merged in GitHub, an agent calls <code class="blog_inline-code">create_deployment</code> to trigger a production deployment in Vercel automatically

Deployment failure response: An agent monitors <code class="blog_inline-code">get_deployment_events</code> for error states and automatically cancels the failed deployment, posts a Slack alert, and opens a GitHub issue with the relevant log output

Secret rotation sync: When a credential rotates in your secrets manager, an agent calls <code class="blog_inline-code">update_env_var</code> to push the new value to the correct Vercel project and environment, keeping config in sync without manual updates

Weekly deployment digest: An agent calls <code class="blog_inline-code">list_deployments</code> each Monday, filters by the past week, and posts a structured summary of deployment activity, error rates, and project status to a shared Slack channel

What are popular tools for Vercel's MCP server?

Here are some of the most commonly used tools:

<code class="blog_inline-code">list_deployments</code> retrieves all deployments for a project, filterable by status, environment, or date range. Good for workflows that need to audit recent activity or check whether a deployment succeeded before taking a downstream action

<code class="blog_inline-code">create_deployment</code> kicks off a new deployment for a specified project and branch. Call this when an agent needs to trigger a release in response to an external event, like a merge, a ticket close, or a scheduled release window

<code class="blog_inline-code">get_deployment_events</code> streams the build and runtime logs for a specific deployment. Useful for agents that need to detect errors, extract build output, or determine why a deployment failed

<code class="blog_inline-code">create_env_var</code> Adds a new environment variable to a Vercel project for a specified environment (production, preview, development). Use this when an agent is provisioning a new project or syncing config from an external source

<code class="blog_inline-code">update_env_var</code> Updates the value of an existing environment variable. Helpful when an agent needs to rotate secrets, update feature flags stored as env vars, or promote a config value from preview to production

<code class="blog_inline-code">pause_project</code> Suspends all incoming requests to a Vercel project. Call this when an agent detects a critical failure and needs to take a project offline immediately while a fix is prepared

What makes Merge Agent Handler's Vercel MCP server better than alternative Vercel MCP servers?

A few things set Merge Agent Handler's Vercel MCP server apart from rolling your own or using a generic alternative:

Enterprise-grade security and DLP: Merge Agent Handler includes built-in data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Vercel, this means you can prevent environment variable values, API tokens, and deployment secrets from being exposed even when the agent has broad read access

Managed authentication and credentials: Merge stores and refreshes Vercel credentials on your behalf. You never expose raw API tokens to an agent or handle token rotation when Vercel credentials change

Real-time observability and audit trail: Every tool call made against Vercel is logged with timestamp, tool name, input parameters, and response metadata. You can audit exactly what an agent deployed, modified, or read without adding any instrumentation yourself

Tool Packs and controlled access: Tool Packs let you bundle specific Vercel tools with tools from other connectors into a single MCP endpoint, scoped to a specific use case. An agent gets exactly the tools it needs, nothing more

How can I start using Merge Agent Handler's Vercel MCP server?

You can take the following steps:

1. Create or log into your Merge Agent Handler account and navigate to Tool Packs (collections of connector tools scoped to a specific use case).

2. Create a new Tool Pack, then find and enable the Vercel connector. Choose which tools to include. You can enable read tools like <code class="blog_inline-code">list_deployments</code> for monitoring use cases, or add write tools like <code class="blog_inline-code">create_deployment</code> and <code class="blog_inline-code">update_env_var</code> if your agent needs to trigger or configure deployments.

3. Add a Registered User inside the Tool Pack. This is the identity context under which your agent operates. Merge generates a unique MCP URL scoped to this user once it's created.

4. From the Registered User detail page, authenticate Vercel by completing the OAuth flow. Merge stores and manages the credentials going forward.

5. Copy the MCP URL from the Tool Pack detail page and generate an API key from Settings. You'll need both to connect your agent.

6. Add the MCP server to your agent or IDE using the MCP URL and API key. Your Vercel tools are now accessible through that endpoint.