Integrations

How it works

BCP exposes a Streamable-HTTP MCP server at /mcp. Claude Desktop runs a small stdio shim (npx mcp-remote) that proxies your local Claude session to the BCP endpoint. Your API key travels on every call as an Authorization: Bearer header; the server filters tool visibility by the key’s permissions and forwards each call to the same backend the REST API uses.

What you can do

• Check a support reply against your brand voice before sending
• Rewrite a Slack draft to fix tone or forbidden words
• Audit ad copy and product descriptions against policy

Try these prompts

Once connected, type these straight into Claude:

1. /load-brand

   Pulls your brand's voice, vocabulary, and governance rules into the session, so everything after this is brand-aware.

2. "Draft a LinkedIn post announcing our new sustainability report. Raw notes: [paste your bullet points]. Keep it on-brand."

   Claude writes it, then self-checks with evaluate_text and revises until it passes — you get the draft plus its on-brand score.

3. "Draft a reply to a customer who received a poor-quality item from an unauthorized reseller — on-brand and within policy."

   Balances empathy with brand protection and stays clear of claims your guardrails don't allow.

4. /policy-check "Audit this ad copy strictly for compliance — ignore tone. [paste copy]"

   Governance-only verdict: flags risky claims, forbidden tactics, and required disclaimers — no tone rewrite.

5. "Rewrite this email in our brand voice and remove any forbidden words: [paste]"

   Returns a before/after with a change log explaining each edit.

Setup

Requires Node.js 18+ (the config runs npx, which ships with Node).

Add this to your Claude Desktop config file:

{
  "mcpServers": {
    "bcp": {
      "command": "npx",
      "args": [
        "-y", "mcp-remote",
        "https://www.brandcontextprotocol.com/mcp",
        "--header",
        "Authorization:Bearer bcp_"
      ]
    }
  }
}

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

Fully quit Claude Desktop (Cmd+Q) and reopen. Ask “What MCP tools do you have available?” to confirm.

How it works

Same MCP server as Claude Desktop. ChatGPT’s native Connectors UI speaks Streamable HTTP directly — no shim needed. Your bearer token is set once in the connector’s auth field; ChatGPT sends it on every tool call.

What you can do

• Score marketing copy mid-draft inside ChatGPT
• Pull brand context into a Custom GPT for on-brand outputs
• Run compliance checks alongside any other tool you’ve connected

Setup

1. Settings → Connectors → Advanced → Developer mode. (Business / Enterprise admins must enable the workspace toggle first.)
2. Add custom connector → URL https://www.brandcontextprotocol.com/mcp
3. Select static-token auth and paste your bcp_… key.

How it works

A Slack-Bolt app served from the BCP backend. A workspace admin completes a one-click OAuth install at /slack/install; BCP stores the workspace’s tokens and links them to a brand. Slash commands and message actions flow into the same evaluation endpoints the REST API uses, so eval logs and usage tracking are unified across surfaces.

What you can do

• Audit a draft message with /brand-check <text>
• Right-click any existing message to score it after the fact
• One-click rewrite to fix tone, forbidden words, or policy violations
• Set per-workspace communication type (support reply, sales email, general)

Setup

1. Click Add to Slack and complete the OAuth install in your workspace.
2. Once installed, a workspace admin runs /brand-guard-setup <api_key> once to bind the workspace to a brand.
3. You’re live — try /brand-check Hello team!

How it works

A private Zendesk app uploaded via Apps & Integrations. It reads the agent’s draft (comment.text) as they type, posts it to POST /api/text/evaluate, and renders the score and top issues inline. One-click rewrite hits POST /api/text/rewrite and writes the result back to the draft. An optional enforceOnSubmit setting blocks ticket.save when the decision is fail. Multi-tenant teams can map each Zendesk org to a different brand via orgBrandMapJson.

What you can do

• Score every draft reply before it sends
• Auto-fix forbidden words and tone misses
• Gate ticket submission on score threshold (configurable)
• Per-Zendesk-org brand routing for managed-service teams

Availability

Available for early-access customers. We’ll send you the private app ZIP and walk you through configuring the API key and brand mapping.

How it works

A Canva app built on Canva’s native app SDK. It loads the brand’s BCP via defaultBrandId or bcpUrl, walks the canvas elements to extract colors, fonts, and logo placements, and posts them to POST /api/design/evaluate (structured) or POST /api/design/analyze-image (rendered). Issues come back with ΔE color-distance values, missing-palette flags, and font-family violations — surfaced inline with one-click auto-fix to the nearest palette match.

What you can do

• Scan canvas elements without leaving the editor
• See a brand-coverage score with per-issue breakdown
• One-click auto-fix off-palette colors
• Catch font and logo violations before export

Availability

Currently in Canva’s app review. Join the early-access list and we’ll notify you when it’s published to the Canva marketplace — and grant private-link access in the meantime.