Use Doctor Rebrand from Claude, Claude Code, or ChatGPT (MCP)

Doctor Rebrand ships a Model Context Protocol server that wraps the public API as MCP tools. Any client that speaks MCP can connect with a PAT and start calling.

Endpoint

https://mcp.doctorrebrand.com/mcp

Auth

Mint a PAT at core.doctorrebrand.com/app/settings/api-tokens and bearer it on every MCP request. The PAT's scopes decide which tools work — start with the read-only preset and add write scopes only when you trust the integration.

Claude.ai or ChatGPT (remote)

In the connector / custom-GPT setup UI, add a new MCP server:

URL: https://mcp.doctorrebrand.com/mcp
Auth: Bearer token = your PAT

Claude Code (local)

Add to ~/.claude/mcp.json (or a project-local .mcp.json):

{
  "mcpServers": {
    "doctor-rebrand": {
      "url": "https://mcp.doctorrebrand.com/mcp",
      "headers": {
        "Authorization": "Bearer …your-token…"
      }
    }
  }
}

What you get

27tools. Every one acts as you, in the organization you're currently working in, and can do nothing you couldn't do in the app. For anything not listed, use the API reference.

Account

`me`	Who the token belongs to, and which partner.	reads
`orgs_memberships`	Your organizations, and your role in each.	reads
`orgs_active`	The organization you're currently working in.	reads
`orgs_plan`	The active organization's plan and subscription status.	reads
`branding`	Your effective brand: name, logo, colors and voice.	reads
`entitlements`	What the organization's plan includes, and how much is used.	reads

Wallet

`wallet_balance`	Token balance: plan tokens, purchased tokens, total.	reads
`wallet_ledger`	Recent token spending and top-ups.	reads
`wallet_reserve_dry_run`	Preview what an operation would cost, without charging.	reads
`operations_catalog`	Every billable operation and its token price.	reads

Content

content_list_articles Articles available to repurpose. reads

Audits

audit_request_create Submit a website for a free audit report. changes data

Client Work

`client_work_list`	Open (or all) Client Work requests.	reads
`client_work_create`	Open a request, optionally with its list of tasks. Nothing is billed until the client approves.	changes data
`client_work_add_items`	Add tasks to an existing request.	changes data
`client_work_orgs`	Client organizations you can open requests for, across partners. (Staff only.)	reads

Cold Email

`coldemail_campaigns`	Your campaigns, their status and headline numbers.	reads
`coldemail_campaign`	One campaign in full: schedule, sequence and results.	reads
`coldemail_replies`	Replies with their category (interested, question, opt-out…).	reads
`coldemail_pause_campaign`	Pause a campaign; leads keep their place.	changes data
`coldemail_resume_campaign`	Start a paused campaign sending again (1 token per email).	spends tokens
`coldemail_add_leads`	Add people to a campaign, with the same checks as an import.	changes data
`coldemail_block`	Block addresses or whole domains from every campaign.	changes data

Reputation

`reputation_summary`	Satisfaction score, response rate, sentiment and who's waiting on a follow-up.	reads
`reputation_responses`	Survey responses and comments, newest first.	reads
`reputation_send_survey`	Schedule a survey for a visit (1 token by email, 3 by text, when it's sent).	spends tokens

Developers

webhooks_list Your outgoing webhook endpoints. reads

Cost safety

For any operation that costs tokens, always use wallet_reserve_dry_run first to preview the cost, surface it to the user, and only proceed if they agree. Operations costing ≥ 10 tokens additionally require an explicit confirmed: trueflag — server-side, regardless of which client is calling. This is your AI's safety belt against runaway spending.