SuperAPI AI Directory
Partner with us中文AI newsFavorites
All toolsAI marketingmcp-audiense-insights

mcp-audiense-insights

Marketing insights and audience analysis from Audiense reports, covering demographic, cultural, influencer, and content engagement analysis.

Open website

About this tool

Purpose

Audiense Insights MCP Server is a server based on the Model Context Protocol (MCP) that enables Claude or any other MCP-compatible client to interact with the user's Audiense Insights account, extracting marketing insights and audience analysis from Audiense reports, covering demographic, cultural, influencer, and content engagement analysis.

Note: This repository is no longer maintained, and Audiense Insights MCP has been migrated to a remote model. To learn how to use the new remote MCP, you can contact support@audiense.com.

Prerequisites

Before use, ensure you have:

  • Node.js (v18 or higher)
  • Claude Desktop App
  • An Audiense Insights account with API credentials
  • X/Twitter API Bearer Token (optional, used to enrich influencer data)

Configure Claude Desktop

Open the Claude Desktop configuration file:

  • macOS: code ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • Windows: code %AppData%\Claude\claude_desktop_config.json

Add or update the following configuration: "mcpServers": { "audiense-insights": { "command": "npx", "args": [ "-y", "mcp-audiense-insights" ], "env": { "AUDIENSE_CLIENT_ID": "your_client_id_here", "AUDIENSE_CLIENT_SECRET": "your_client_secret_here", "TWITTER_BEARER_TOKEN": "your_token_here" } } }

Save the file and restart Claude Desktop.

Available Tools

  • get-reports: Get a list of Audiense insights reports owned by the authenticated user. No parameters; returns a JSON-formatted list of reports.
  • get-report-info: Get detailed information about a specific intelligence report, including segmentation types, etc. The parameter is report_id (string); returns the full report details in JSON format, or pending status information if the report is still being processed.
  • get-audience-insights: Get aggregated insights for a given audience, including demographics (gender, age, country), behavioral characteristics (active times, platform usage), psychographic characteristics (personality traits, interests), and socioeconomic factors (income, education status). The parameters are audience_insights_id (string) and optional insights (string array, used to filter specific insight names); returns insights in a structured text list format.
  • get-baselines: Get available baseline audiences, filterable by country. The parameter is optional country (ISO country code); returns a JSON-formatted list of baseline audiences.
  • get-categories: Get a list of available affinity categories for influencer comparison. Returns a JSON-formatted list of categories.
  • compare-audience-influencers: Compare the influencers of a given audience with a baseline audience. Baseline determination method: if a single country accounts for more than 50% of the audience, use that country as the baseline; otherwise use the global baseline; if a specific segment is selected, use the full audience as the baseline. Each influencer comparison includes affinity (%), baseline affinity (%), and uniqueness score. Parameters include audience_influencers_id, baseline_audience_influencers_id, optional cursor, count (default 200), bio_keyword, entity_type (person | brand), followers_min, followers_max, categories, countries; returns a JSON-formatted list of influencers including affinity scores, baseline comparisons, and uniqueness scores.
  • get-audience-content: Get details of audience content engagement, including liked content (most popular posts, domains, emojis, hashtags, links, media, and word clouds), shared content (categorized similarly), influential content (from influential accountscontent of the household). The response parameter is audience_content_id (string); returns content interaction data in JSON format.
  • report-summary: generates a comprehensive summary of an Audiense report, including report metadata (title, segment type), full audience size, detailed segment information, top insights for each segment (bio keywords, demographics, interests), top influencers for each segment, and comparison metrics. The parameter is report_id (string); returns a complete report summary in JSON format. Reports in progress return processing status information; reports without segments return information that there are no segments to analyze.

Predefined Prompts

This server contains preconfigured prompts:

  • audiense-demo: helps analyze Audiense reports interactively.
  • segment-matching: used to match and compare audience segments across Audiense reports, identifying similarities, unique characteristics, and key insights based on demographics, interests, influencers, and interaction patterns. Accepts a reportName parameter to find the most relevant report; if an ID is provided, searches by report ID. Provides structured guidance for audience analysis.

Troubleshooting

  • Tools not showing in Claude: check Claude Desktop logs; verify environment variables are set correctly; ensure the absolute path to index.js is correct.
  • Authentication issues: carefully check OAuth credentials; ensure the refresh token is still valid; verify that the required API scopes are enabled.
  • View server logs on macOS/Linux.

Security Considerations

  • Keep API credentials secure—never expose them in public repositories.
  • Use environment variables to manage sensitive data.

License

This project uses the Apache 2.0 license, see the LICENSE file for details.

Related tools

Browse category