Messari Influencer Mindshare and Asset Analysis

What is Messari Influencer Mindshare and Asset Analysis?

A Python-based MCP server that analyzes mindshare data for cryptocurrency assets and Key Opinion Leaders (KOLs) using the Messari API. It fetches daily mindshare scores, detects anomalies via z-scores, visualizes trends in Google Colab, and optionally enriches anomalies with sentiment analysis via the Mistral API. Designed for crypto researchers and traders tracking market attention shifts.

How to use Messari Influencer Mindshare and Asset Analysis?

Configure the server by navigating to server.py and ensuring a valid Messari API key is set. The repository includes a Colab notebook (LLM_Mindshare_asset_analysis.ipynb) and a server module. Users run the server to trigger data fetching, anomaly detection, and visualization. Key functions include analyze_mindshare_data (for KOL handles) and analyze_asset_mindshare (for asset slugs).

Key features of Messari Influencer Mindshare and Asset Analysis

• Fetches daily mindshare data via the Messari API
• Detects anomalies using z-scores (default threshold: 2.0)
• Plots mindshare scores over time with highlighted anomalies
• Provides readable insights on trends, score/rank ranges, and dates
• Calls Mistral API for sentiment analysis on trending topics
• Caches Mistral responses and retries on rate limits

Use cases of Messari Influencer Mindshare and Asset Analysis

• Track mindshare spikes for a crypto asset like official-trump
• Monitor KOL influence by analyzing Twitter handle mindshare
• Correlate anomalies with trending topics and market news
• Generate actionable insights for trading or marketing strategies
• Compare asset mindshare trends side by side in Colab

FAQ from Messari Influencer Mindshare and Asset Analysis

What APIs does it use?

It uses the Messari Copilot Agent, Current Topics, X-Users Mindshare Over Time, Mindshare of Asset Over Time, and Asset Details APIs.

What are the runtime requirements?

The analysis is designed for Google Colab, with interactive plotting. An optional Mistral API key enables sentiment analysis; the script includes retry logic and caching.

How does it detect anomalies?

Anomalies are identified using z-scores with a default threshold of 2.0. Points with absolute z-score above the threshold are flagged and highlighted in plots.

Can it analyze both assets and influencers?

Yes. analyze_asset_mindshare works on asset slugs (e.g., mantra-dao), while analyze_mindshare_data works on Twitter handles (e.g., @AltcoinGordon).

Where does the data live?

Mindshare data is fetched live from the Messari API. No data is stored locally; results are displayed directly in the Colab notebook.