`timeline_tone`

Pack: gdelt · Endpoint: https://gateway.pipeworx.io/gdelt/mcp

Day-by-day AVERAGE NEWS SENTIMENT for a GDELT query over time. Returns datapoints with timestamp + tone value (-100 very negative .. +100 very positive, computed from GDELT’s sentiment scoring of every article matching the query). Use for tracking sentiment shifts around a topic, person, country, or event (“how did press coverage of X change after Y happened”). Pair with timeline_volume to chart sentiment vs interest — interest spike + sentiment drop = something bad just happened.

Parameters

Name	Type	Required	Description
`query`	string	yes	GDELT query string
`timespan`	string	no	Lookback window (default “1m” — month)
`startdatetime`	string	no	YYYYMMDDHHMMSS — only with timespan=custom
`enddatetime`	string	no	YYYYMMDDHHMMSS — only with timespan=custom

Example call

Arguments

{
  "query": "Bitcoin sourcelang:eng"
}

curl

curl -X POST https://gateway.pipeworx.io/gdelt/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"timeline_tone","arguments":{"query":"Bitcoin sourcelang:eng"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('timeline_tone', {
  "query": "Bitcoin sourcelang:eng"
});

More examples

{
  "query": "Trump sourcecountry:US",
  "timespan": "custom",
  "startdatetime": "20231201000000",
  "enddatetime": "20240101000000"
}

Response shape

Always returns: query, timespan, metric, points, series

Field	Type	Description
`query`	string	The query string used
`timespan`	string	Lookback window applied (default 1m)
`metric`	string	Metric type: avg_tone (-100..+100)
`points`	number	Number of datapoints returned
`series`	array	Day-by-day tone datapoints

Full JSON Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The query string used"
    },
    "timespan": {
      "type": "string",
      "description": "Lookback window applied (default 1m)"
    },
    "metric": {
      "type": "string",
      "description": "Metric type: avg_tone (-100..+100)"
    },
    "points": {
      "type": "number",
      "description": "Number of datapoints returned"
    },
    "series": {
      "type": "array",
      "description": "Day-by-day tone datapoints",
      "items": {
        "type": "object",
        "properties": {
          "date": {
            "type": "string",
            "description": "Date of datapoint"
          },
          "value": {
            "type": "number",
            "description": "Average tone value for the day"
          }
        },
        "required": [
          "date",
          "value"
        ]
      }
    }
  },
  "required": [
    "query",
    "timespan",
    "metric",
    "points",
    "series"
  ]
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "gdelt": {
      "url": "https://gateway.pipeworx.io/gdelt/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

timeline_tone