Server definition

Hash: sha256:7b0bf8934edb04dfc43f34c87e8dd93b4b266ba6ada41748ce6a35ff7d2e0221
What it is: What a remote MCP server returned when asked what it offers: 2 tools

The blob, as servednamed by its sha256

{
  "instructions": null,
  "tools": [
    {
      "description": "Use this when you need to determine the emotional tone and sentiment of text. Returns structured sentiment analysis with emotion breakdown and key drivers.\n\n1. sentiment: overall sentiment label (positive, negative, neutral)\n2. confidence: confidence score 0-100\n3. emotions: detected emotions with scores (joy, anger, fear, surprise, sadness)\n4. keyPhrases: array of phrases driving the sentiment\n5. score: numeric sentiment score from -1.0 (negative) to 1.0 (positive)\n\nExample output: {\"sentiment\":\"positive\",\"confidence\":87,\"score\":0.73,\"emotions\":{\"joy\":0.82,\"surprise\":0.15,\"anger\":0.01,\"fear\":0.01,\"sadness\":0.01},\"keyPhrases\":[\"excellent results\",\"exceeded expectations\"]}\n\nUse this BEFORE responding to customer feedback, reviews, or social media mentions. Essential for brand monitoring, support ticket triage, and content tone analysis.\n\nDo NOT use for summarization -- use ai_summarize_text. Do NOT use for content extraction -- use web_scrape_to_markdown. Do NOT use for text classification -- use text_classify_content.",
      "inputSchema": {
        "properties": {
          "text": {
            "description": "The text to analyze for sentiment",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "text_analyze_sentiment",
      "outputSchema": null
    },
    {
      "description": "Use this when you need to analyze sentiment of multiple texts at once (up to 20). Returns an array of individual sentiment results in one call.\n\n1. results: array of sentiment objects, one per input text\n2. Each result contains: sentiment, confidence, score, emotions, keyPhrases\n3. averageSentiment: overall average sentiment score across all texts\n4. distribution: count of positive/negative/neutral texts\n\nExample output: {\"results\":[{\"sentiment\":\"positive\",\"confidence\":91,\"score\":0.8},{\"sentiment\":\"negative\",\"confidence\":74,\"score\":-0.6}],\"averageSentiment\":0.1,\"distribution\":{\"positive\":1,\"negative\":1,\"neutral\":0}}\n\nUse this FOR bulk analysis of reviews, survey responses, or social media feeds. Essential when comparing sentiment across multiple data points.\n\nDo NOT use for single text -- use text_analyze_sentiment. Do NOT use for text classification -- use text_classify_content. Do NOT use for language detection -- use text_detect_language.",
      "inputSchema": {
        "properties": {
          "texts": {
            "description": "Array of texts to analyze (max 20)",
            "items": {
              "type": "string"
            },
            "type": "array"
          }
        },
        "required": [
          "texts"
        ],
        "type": "object"
      },
      "name": "text_analyze_sentiment_batch",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:7b0bf8934edb04dfc43f34c87e8dd93b4b266ba6ada41748ce6a35ff7d2e0221 | sha256sum