Provider REST API

11 actions

Connect Claude to Vercel

Inspect projects, deployments, domains, and build logs. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Access token
Actions exposed: 11
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Vercel
Open the marketplace in your workspace, add Vercel to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with access token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Vercel shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Vercel asks for

Access token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Access tokenRequired: Vercel dashboard → Account Settings → Tokens. Scope the token to the team you want this tool to reach.; vercel_…
Default team IDOptional: Settings → General on the team page. Leave empty for a personal account; individual calls can still override it.; team_…

What Claude can do in Vercel

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 9Reads
Writes: 2Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_projects
List projects for the account or team, with each project's latest deployment. Start here when you need a project id or name.
get_project
Retrieve one project's full settings by id or name: framework, build and install commands, root directory, regions, and protection settings. Environment variables are omitted - use list_env_vars for those.
list_deployments
List deployments newest first, optionally scoped to one project, environment, branch, or state. Use to find the deployment that is live, or the one that failed.
get_deployment
Retrieve one deployment by id or hostname: state, target, aliases, commit metadata, and any error code. Call deployment_logs for the build output itself.
deployment_logs
Return the build log lines for a deployment, newest first by default. This is a different endpoint from get_deployment - use it to find out why a build failed.
list_project_domains
List the domains attached to a project, including verification state and any redirect target.
list_env_vars
List a project's environment variables: key, target environments, type, and comment. Values are never returned - use this to check which variables exist and where they apply.
list_teams
List the teams this token can reach, with their ids and slugs. Call this when you need a team_id for the other actions.
whoami
Return the account that owns this token: id, username, email, and default team. Use to confirm which account the credential reaches.

Writes

Creates or updates something on the other side.

add_project_domain
Attach a domain to a project, optionally as a redirect or pinned to a Git branch. Returns verified:false plus a DNS challenge when the domain still needs verification. Remove a domain from the Vercel dashboard - this tool does not delete domains.
upsert_env_var
Create an environment variable on a project, or overwrite its value if the key already exists for the same targets. The new value only reaches the site after the next deployment.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches Vercel rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Vercel, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Vercel of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Vercel: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Vercel. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Vercel's own rate limits. A call that Vercel refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Vercel?

11 named actions: 9 that only read and 2 that write. They include list_projects, get_project and list_deployments. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Vercel connector need?

Access token. The connector asks for access token, and optionally default team id. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Vercel connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Vercel connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Vercel rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Vercel, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Vercel of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Vercel. An agent has to ask. Toolspoke does not retry, queue or back off around Vercel's own rate limits. A call that Vercel refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Vercel's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Vercel?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More infrastructure connectors

Browse all of them