F
licenseNot graded
qualityD
maintenanceEnables content generation and style application using Jasper AI's marketing platform. Supports brand voices, style guides, and audience targeting for creating on-brand content through natural language.
-
Marketing Brain
by Felipe-Cal
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Marketing Brainget the content strategy for a blog post"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Marketing Brain MCP Server
A lightweight Model Context Protocol (MCP) server that acts as a "Marketing Brain," providing standardized brand guidelines and content templates.
Features
Brand Voice Source of Truth: Exposes the core brand guidelines (Voice, Audience, Constraints) through a simple tool.
Content Templates: Provides structured templates for common marketing assets (Blog, Email, Social).
Extensible Design: Uses a file-based system. Add or edit Markdown files in the
data/directory to update strategies or add new ones without changing the code.SSE Support: Ready for cloud deployment via Server-Sent Events (SSE).
Related MCP server: BrandKit MCP
Tools
get_content_strategy
Returns the brand guidelines combined with a specific asset template.
Input:
asset_type(str) - e.g.,blog,email,social.
Project Structure
server.py: The FastMCP server application.data/brand_guidelines.md: The global brand identity.data/templates/: Folder containing individual template files (one.mdfile per template).
Installation & Usage
1. Cloud Deployment (Remote)
The server is optimized for deployment on platforms like Railway or Render.
Once deployed, you can connect your MCP client (like Claude Desktop) using the SSE endpoint:
{
"mcpServers": {
"marketing-brain": {
"url": "https://marketing-brain-mcp.railway.app/sse"
}
}
}2. Local Development
Prerequisites
Python 3.10+
pip install fastmcp
Running Locally (Stdio)
For local testing in your AI assistant:
fastmcp run server.pyDevelopment Inspector
To test the tools in a web interface:
fastmcp dev server.py3. Smithery
You can also install this server using the Smithery CLI:
npx -y @smithery/cli install github.com/Felipe-Cal/marketing-brain-mcp --client claudeLicense
MIT
Available Tools
1 toolget_content_strategyA
Get the content strategy and template for a specific asset type.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| asset_type | Yes | The type of asset to generate strategy for. (e.g., 'blog', 'email', 'social') |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
A3.6/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only indicates a read operation ('Get'), but without annotations, it fails to disclose behavioral traits such as authentication needs, rate limits, or error handling for unknown asset types. This leaves gaps in agent understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that conveys the core purpose without unnecessary words. It is front-loaded with the action 'Get'.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with one parameter and an output schema, the description provides adequate context by stating what is retrieved. It does not need to elaborate on return values due to output schema existence.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the 'asset_type' parameter with examples. The tool description adds no additional meaning beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'Get' and the resource 'content strategy and template' for a specific asset type, leaving no ambiguity about the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a content strategy or template for a given asset type is needed, but provides no explicit guidance on when not to use or alternatives. With no sibling tools, this is less critical but still lacking.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
get_content_strategy
TDQS
A3.5/5.0
Scored across 1 tool
Disambiguation5/5
Only one tool exists, so there is no risk of confusing it with another tool. The tool's purpose is clear and unambiguous.
Naming Consistency5/5
With a single tool, naming consistency is trivially maintained. The name 'get_content_strategy' follows a clear verb_noun pattern.
Tool Count2/5
The server is named 'Marketing Brain,' which implies a broad scope covering multiple marketing functions. Having only one tool is insufficient for this purpose, making the count too small.
Completeness1/5
A single 'get' operation is severely incomplete for a marketing strategy domain. Missing operations like create, update, delete, or analyze leave obvious gaps that agents cannot work around.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Brand-safe MCP for AI agents to create editable, on-brand graphics and automate variants.
Digital asset manager - upload, organize, search, and generate on-brand images and videos
- OrshotOAuthcom.orshot
Render on-brand images, PDFs and videos from templates. 60+ tools: brand kit, folders, workflows.
Access and maintain design system docs, tokens, components, skills, and contexts across any project.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP for deploying BrandKit guardrails to LLMs across your organization.1247 npm5MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that exposes brand identity guidelines (visual look and voice) as markdown, enabling LLMs to produce on-brand content.3 npmMIT
- FlicenseNot gradedqualityBmaintenanceThe context layer for GTM teams — one source of truth for brand and company context, so your whole team produces consistent, on-brand content in any AI tool.-