🚀 Unleashing AI-Powered Marketing Insights: The Audiense Insights MCP Server

Unlock the power of your Audiense Insights data with seamless integration into Large Language Model (LLM) applications using the Model Context Protocol (MCP). This server empowers Claude and other MCP-compatible clients to access and leverage rich marketing insights and audience analysis directly from your Audiense reports, covering demographic, cultural, influencer, and content engagement analysis.

---

🛠️ Essential Prerequisites

Before diving in, ensure you have the following ready:

• Node.js: Version 18 or higher is required.
• Claude Desktop App: The client application for interacting with the server.
• Audiense Insights Account: An active account with valid API credentials.
• X/Twitter API Bearer Token: (Optional) Enhance influencer data with real-time Twitter insights.

---

📦 Installation via Smithery (Recommended)

The easiest way to install the Audiense Insights Server for Claude Desktop is through Smithery:

npx -y @smithery/cli@latest install @AudienseCo/mcp-audiense-insights --client claude

This command automates the installation process, streamlining setup.

⚙️ Manual Configuration of Claude Desktop

1. Locate the Configuration File:

   • MacOS:

     code ~/Library/Application\ Support/Claude/claude_desktop_config.json

   • Windows:

     code %AppData%\Claude\claude_desktop_config.json

2. Add or Update the mcpServers Configuration:

   "mcpServers": {
     "audiense-insights": {
       "command": "/opt/homebrew/bin/node",
       "args": [
         "/ABSOLUTE/PATH/TO/YOUR/build/index.js"
       ],
       "env": {
         "AUDIENSE_CLIENT_ID": "your_client_id_here",
         "AUDIENSE_CLIENT_SECRET": "your_client_secret_here",
         "TWITTER_BEARER_TOKEN": "your_token_here"
       }
     }
   }

   • Important: Replace /ABSOLUTE/PATH/TO/YOUR/build/index.js with the actual path to your index.js file.
   • Populate AUDIENSE_CLIENT_ID, AUDIENSE_CLIENT_SECRET, and TWITTER_BEARER_TOKEN with your respective credentials.

3. Restart Claude Desktop: Save the configuration file and restart the application for the changes to take effect.

🧰 Available Tools: A Deep Dive

This server provides a suite of powerful tools to extract and analyze Audiense Insights data.

📌 get-reports: Unveiling Your Audiense Report Portfolio

Description: Retrieves a comprehensive list of Audiense Insights reports associated with your authenticated account.

• Parameters: None
• Response: A JSON array containing metadata for each report.

---

📌 get-report-info: Decoding the DNA of an Intelligence Report

Description: Provides detailed information about a specific Audiense Intelligence report, including:

• Status (e.g., processing, completed)

• Segmentation type (e.g., demographic, interest-based)

• Audience size

• Segments defined within the report

• Direct access links to the report in Audiense

• Parameters:

  • report_id (string): The unique identifier of the intelligence report.

• Response: A JSON object containing the full report details. If the report is still processing, a status message is returned.

---

📌 get-audience-insights: Illuminating Audience Characteristics

Description: Extracts aggregated insights for a given audience, providing a holistic view of their attributes:

• Demographics: Gender, age distribution, geographic location (country).

• Behavioral Traits: Active hours online, preferred social media platforms.

• Psychographics: Personality traits, core interests, values.

• Socioeconomic Factors: Income level, education status, occupation.

• Parameters:

  • audience_insights_id (string): The ID of the audience insights data.
  • insights (array of strings, optional): A list of specific insight names to filter the results (e.g., ["gender", "interests"]).

• Response: A structured text list of insights, ideal for feeding into LLMs.

---

📌 get-baselines: Establishing Benchmarks for Comparison

Description: Retrieves a list of available baseline audiences, which can be used for comparative analysis.

• Parameters:

  • country (string, optional): An ISO country code to filter the baseline audiences by location (e.g., "US" for the United States).

• Response: A JSON array containing metadata for each baseline audience.

---

📌 get-categories: Navigating the Affinity Landscape

Description: Retrieves a list of available affinity categories, which are used to categorize influencers based on their areas of expertise and interest.

• Parameters: None
• Response: A JSON array containing the names and descriptions of each affinity category.

---

📌 compare-audience-influencers: Identifying Key Voices

Description: Compares the influencers of a target audience with a baseline audience, providing valuable insights into the unique voices that resonate with the target group. The baseline audience is determined automatically:

• If a single country represents more than 50% of the audience, that country is used as the baseline.
• Otherwise, the global baseline is used.
• If a specific segment is selected, the full audience is used as the baseline.

Each influencer comparison includes:

• Affinity (%): How well the influencer aligns with the target audience.

• Baseline Affinity (%): The influencer's affinity within the baseline audience.

• Uniqueness Score: How distinct the influencer is compared to the baseline.

• Parameters:

  • audience_influencers_id (string): The ID of the target audience's influencer data.
  • baseline_audience_influencers_id (string): The ID of the baseline audience's influencer data.
  • cursor (number, optional): Pagination cursor for retrieving large datasets.
  • count (number, optional): Number of influencers to retrieve per page (default: 200).
  • bio_keyword (string, optional): Filter influencers by keywords found in their Twitter bio.
  • entity_type (enum: person | brand, optional): Filter by whether the influencer is an individual or a brand.
  • followers_min (number, optional): Minimum number of followers the influencer must have.
  • followers_max (number, optional): Maximum number of followers the influencer can have.
  • categories (array of strings, optional): Filter influencers by affinity categories.
  • countries (array of strings, optional): Filter influencers by country ISO codes.

• Response: A JSON array containing a list of influencers with their affinity scores, baseline comparison, and uniqueness scores.

---

📌 get-audience-content: Deciphering Content Engagement Patterns

Description: Retrieves detailed information about the content that resonates most with the target audience, including:

• Liked Content: Most popular posts, domains, emojis, hashtags, links, media, and a word cloud.
• Shared Content: Most shared content, categorized similarly to liked content.
• Influential Content: Content originating from influential accounts within the audience.

Each category contains:

• popularPost: Most engaged posts.

• topDomains: Most mentioned domains.

• topEmojis: Most used emojis.

• topHashtags: Most used hashtags.

• topLinks: Most shared links.

• topMedia: Shared media.

• wordcloud: Most frequently used words.

• Parameters:

  • audience_content_id (string): The ID of the audience content data.

• Response: A JSON object containing the content engagement data.

---

📌 report-summary: Synthesizing a Comprehensive Overview

Description: Generates a comprehensive summary of an Audiense report, providing a high-level overview of the key findings.

• Report metadata (title, segmentation type)

• Full audience size

• Detailed segment information

• Top insights for each segment (bio keywords, demographics, interests)

• Top influencers for each segment with comparison metrics

• Parameters:

  • report_id (string): The ID of the intelligence report to summarize.

• Response: A JSON object containing the complete report summary, with structured data for each segment. For pending reports, a status message is returned. For reports without segments, a message indicating there are no segments to analyze is returned.

🧠 Predefined Prompts: Jumpstart Your Analysis

This server includes preconfigured prompts to accelerate your analysis:

• audiense-demo: Facilitates interactive exploration of Audiense reports.
• segment-matching: Compares audience segments across Audiense reports, identifying similarities, unique traits, and key insights based on demographics, interests, influencers, and engagement patterns.

Usage:

• Accepts a reportName argument to find the most relevant report.
• If an ID is provided, it searches by report ID instead.

Use Case: Provides structured guidance for in-depth audience analysis.

🐛 Troubleshooting: Resolving Common Issues

Tools Not Appearing in Claude

1. Check Claude Desktop Logs:

   tail -f ~/Library/Logs/Claude/mcp*.log

2. Verify Environment Variables: Ensure all required environment variables are set correctly.

3. Confirm Path Accuracy: Double-check the absolute path to index.js in the configuration.

Authentication Issues

• Credential Verification: Double-check your Audiense OAuth credentials.
• Refresh Token Validity: Ensure your refresh token is still valid.
• API Scope Confirmation: Verify that the necessary API scopes are enabled in your Audiense application.

🪵 Viewing Logs: Monitoring Server Activity

To monitor the server's activity and diagnose potential issues, view the logs:

MacOS/Linux:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Windows:

Get-Content -Path "$env:AppData\Claude\Logs\mcp*.log" -Wait -Tail 20

🔒 Security Considerations: Protecting Sensitive Data

• Credential Management: Never expose API credentials in public repositories.
• Environment Variables: Utilize environment variables to securely manage sensitive data.