
Amazon Ads MCP Server
The Amazon Ads MCP Server bridges AI assistants and Amazon Advertising by providing seamless programmatic access to campaign management, reporting, recommendati...
Connect your AI flows to Facebook Ads for seamless campaign management, reporting, and automation—securely and efficiently with the Facebook Ads MCP Server.
The Facebook Ads MCP Server is a Model Context Protocol (MCP) server that acts as an interface to the Facebook Ads platform, allowing AI assistants and development environments to programmatically access and manage Facebook Ads data. By connecting this MCP server to your AI client, you can automate tasks such as querying ad performance, managing campaigns, and accessing reports, all without the need to manually interact with the Facebook Ads UI. The server streamlines authentication—either prompting for your access token or generating one for you via GoMarble’s secure infrastructure—making the setup simple. This integration empowers developers to build, manage, and analyze ad campaigns more efficiently by leveraging AI-driven workflows and automations.
No information found in the repository regarding available prompt templates.
No explicit resource definitions found in the repository or documentation.
No explicit tool list found in the documentation or in the visible server.py description. The section “Available MCP Tools” is present in the readme, but no further details are provided within the retrieved content.
Ensure Python 3.10+ is installed and dependencies in requirements.txt
are satisfied.
Obtain a Facebook Access Token with the necessary permissions.
Locate your Windsurf configuration file.
Add the Facebook Ads MCP Server to the mcpServers
section:
{
"mcpServers": {
"fb-ads-mcp-server": {
"command": "python",
"args": [
"/path/to/your/fb-ads-mcp-server/server.py",
"--fb-token",
"YOUR_FACEBOOK_ACCESS_TOKEN"
]
}
}
}
Save the config and restart Windsurf. Verify the MCP server appears in the interface.
Use environment variables to secure your access token:
{
"mcpServers": {
"fb-ads-mcp-server": {
"command": "python",
"args": [
"/path/to/your/fb-ads-mcp-server/server.py",
"--fb-token",
"${FACEBOOK_ACCESS_TOKEN}"
],
"env": {
"FACEBOOK_ACCESS_TOKEN": "your-token-value"
}
}
}
}
Install Python 3.10+ and dependencies from requirements.txt
.
Obtain a Facebook Access Token.
Edit the Claude configuration as follows:
{
"mcpServers": {
"fb-ads-mcp-server": {
"command": "python",
"args": [
"/path/to/your/fb-ads-mcp-server/server.py",
"--fb-token",
"YOUR_FACEBOOK_ACCESS_TOKEN"
]
}
}
}
Save and restart Claude. Verify the server connection.
Install Python 3.10+ and dependencies.
Acquire a Facebook Access Token.
Update the Cursor MCP configuration:
{
"mcpServers": {
"fb-ads-mcp-server": {
"command": "python",
"args": [
"/path/to/your/fb-ads-mcp-server/server.py",
"--fb-token",
"YOUR_FACEBOOK_ACCESS_TOKEN"
]
}
}
}
Restart Cursor after saving changes.
Ensure Python 3.10+ and dependencies are installed.
Secure your Facebook Access Token.
Edit the Cline configuration file:
{
"mcpServers": {
"fb-ads-mcp-server": {
"command": "python",
"args": [
"/path/to/your/fb-ads-mcp-server/server.py",
"--fb-token",
"YOUR_FACEBOOK_ACCESS_TOKEN"
]
}
}
}
Save and restart Cline.
Always use environment variables for sensitive credentials (see JSON examples above).
Using MCP in FlowHunt
To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:
Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:
{
"facebook-ads-mcp": {
"transport": "streamable_http",
"url": "https://yourmcpserver.example/pathtothemcp/url"
}
}
Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “facebook-ads-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.
Section | Availability | Details/Notes |
---|---|---|
Overview | ✅ | Overview, setup, and usage information found |
List of Prompts | ⛔ | No prompt templates listed |
List of Resources | ⛔ | No explicit resources described |
List of Tools | ⛔ | “Available MCP Tools” section exists, but not detailed |
Securing API Keys | ✅ | Instructions for using env variables |
Sampling Support (less important in evaluation) | ⛔ | No info |
Between the sections above, the Facebook Ads MCP Server provides solid setup documentation but lacks public documentation on prompts, explicit tools, and resources. Its key strength is ease of integration and clear credential management. Based on documentation completeness and transparency, I would rate this MCP server a 5/10.
Has a LICENSE | ✅ (MIT) |
---|---|
Has at least one tool | ⛔ |
Number of Forks | 14 |
Number of Stars | 68 |
The Facebook Ads MCP Server is a bridge between FlowHunt (and other AI agents) and the Facebook Ads platform. It enables automated management of campaigns, access to performance analytics, and secure credential handling within your AI workflows.
You can automate campaign management, fetch real-time performance reports, run bulk ad operations, and enable AI assistants to analyze and optimize your Facebook Ads—all programmatically.
You should use environment variables in your configuration files to prevent exposing sensitive credentials. See the example configurations for each client above for details.
The current documentation does not list any specific tool or prompt template. Its main focus is on providing a robust API bridge for Facebook Ads data and actions.
You need Python 3.10+, required dependencies (see requirements.txt), and a Facebook Access Token with appropriate permissions. Follow the step-by-step instructions for your AI client to configure and launch the server.
Integrate the Facebook Ads MCP Server with FlowHunt to automate campaign workflows, streamline reporting, and unlock AI-powered optimization for your ad operations.
The Amazon Ads MCP Server bridges AI assistants and Amazon Advertising by providing seamless programmatic access to campaign management, reporting, recommendati...
The Model Context Protocol (MCP) Server bridges AI assistants with external data sources, APIs, and services, enabling streamlined integration of complex workfl...
The ModelContextProtocol (MCP) Server acts as a bridge between AI agents and external data sources, APIs, and services, enabling FlowHunt users to build context...