MCP Server

The Manna MCP Server lets you manage your brands, generate content, and publish posts from any AI assistant that supports the Model Context Protocol (MCP). Instead of switching between Brandmanna and your AI tools, you can do everything through conversation.

What is MCP?

The Model Context Protocol is an open standard that connects AI assistants to external data sources and tools. When you install the Manna MCP Server, your AI assistant gains direct access to your Brandmanna account — your brands, drafts, ideas, calendar, and publishing connections.

Prerequisites

Before you begin, you need:

A Brandmanna account.
An API key. Generate one in Account Settings > API Keys. See API Keys for details.
Python 3.10 or later (for pip install) or uvx (recommended).

Installation

Install the server using pip:

pip install manna-mcp

Or run it directly with uvx (no install required):

uvx manna-mcp

Configuration

The server uses two environment variables:

Variable	Required	Description
`MANNA_API_KEY`	Yes	Your Brandmanna API key (starts with `manna_`)
`MANNA_API_URL`	No	API base URL. Defaults to `https://api.brandmanna.com`

export MANNA_API_KEY="manna_your_key_here"
export MANNA_API_URL="https://api.brandmanna.com"

Setup Guides

Claude Desktop

Add the following to your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "manna": {
      "command": "uvx",
      "args": ["manna-mcp"],
      "env": {
        "MANNA_API_KEY": "manna_your_key_here"
      }
    }
  }
}

Replace manna_your_key_here with your actual API key. Restart Claude Desktop after saving the file.

Cursor

Add the following to your Cursor MCP settings:

{
  "manna": {
    "command": "uvx",
    "args": ["manna-mcp"],
    "env": {
      "MANNA_API_KEY": "manna_your_key_here"
    }
  }
}

VS Code

Add the following to your VS Code MCP settings:

{
  "manna": {
    "command": "uvx",
    "args": ["manna-mcp"],
    "env": {
      "MANNA_API_KEY": "manna_your_key_here"
    }
  }
}

Available Tools

Once connected, your AI assistant can use these tools:

Tool	Description
`list_brands`	List all brands in your account
`get_brand`	Get full brand profile with voice fingerprint
`generate_ideas`	Generate content ideas from a brief
`generate_quick_draft`	One-shot draft generation
`generate_draft_from_idea`	Turn banked ideas into drafts
`list_drafts`	Browse your content drafts
`get_draft`	Get a specific draft
`refine_draft`	Improve draft clarity, tone, or length
`score_content`	Score content against brand voice
`schedule_draft`	Schedule a draft for a date/time
`publish_draft`	Auto-publish to connected social accounts
`get_calendar_intelligence`	Content calendar analysis and recommendations
`list_ideas`	Browse banked content ideas

Resources

Resources provide read-only context that your AI assistant can reference during conversations:

Resource URI	Description
`manna://brands`	List of all your brands with basic info
`manna://brands/{id}`	Full brand voice profile for a specific brand

You can inject a brand's voice profile into any conversation to give your AI assistant full context about your brand identity, voice, tone, and messaging.

Prompts

Prompts are guided workflows that structure how you interact with Brandmanna through your AI assistant:

Prompt	Description
Draft Post	Draft a social media post for a brand
Review Draft	Review content against brand voice guidelines
Content Ideas	Generate and present content ideas

Example Usage

Once the MCP server is connected, you can interact with Brandmanna naturally. For example:

"List my brands and show me the voice profile for Acme Corp."
"Generate 5 LinkedIn post ideas about product launches for my brand."
"Score this draft against my brand voice and suggest improvements."
"Schedule my latest draft for next Tuesday at 9am."

Your AI assistant will call the appropriate Manna tools behind the scenes and present the results in the conversation.

On this page