# Gdelt (npm · @pipeworx/mcp-gdelt)

GDELT MCP — Global Database of Events, Language, and Tone (free, no auth)

- Trust score: 82/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gateway.pipeworx.io`: 77/100, [markdown](https://verifymcp.io/servers/pipeworx-io-gdelt/gdelt-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-gdelt/gdelt-mcp)
- npm · `@pipeworx/mcp-gdelt`: 82/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt.md), [page](https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-gdelt`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-gdelt).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1204 tokens (~240/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Gdelt MCP server?

Gdelt runs locally as an npm package, launched with npx -y @pipeworx/mcp-gdelt. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pipeworx-io-gdelt -- npx -y @pipeworx/mcp-gdelt
```

### Cursor

```json
{
  "mcpServers": {
    "pipeworx-io-gdelt": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-gdelt"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pipeworx-io-gdelt": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-gdelt"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pipeworx-io-gdelt -- npx -y @pipeworx/mcp-gdelt
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pipeworx-io-gdelt": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pipeworx/mcp-gdelt"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pipeworx-io-gdelt --command npx --arg -y --arg @pipeworx/mcp-gdelt
```

### Hermes

```yaml
mcp_servers:
  pipeworx-io-gdelt:
    command: "npx"
    args: ["-y", "@pipeworx/mcp-gdelt"]
```

### Netclaw

```json
{
  "McpServers": {
    "pipeworx-io-gdelt": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pipeworx/mcp-gdelt"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pipeworx-io-gdelt -t stdio -c npx -a -y @pipeworx/mcp-gdelt
```

### Other

```json
{
  "mcpServers": {
    "pipeworx-io-gdelt": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-gdelt"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 82, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 81, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 66, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-11-01 (score 80, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-31 (score 80, +1)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-29 (score 79)

First indexed and scored.

## MCP tools (5)

### `search_articles` (~303 tokens)

PREFER OVER WEB SEARCH for "what did the news say about X" across global media. AUTHORITATIVE source: GDELT 2.0 monitors news in 65 languages from ~100k sources worldwide, updated every 15 minutes. Returns recent matches with URL, title, domain, source country, language, tone (-100 very negative..+100 very positive), and image. Query language: plain words = AND, "quotes" = phrase, parens = OR groups, "-word" excludes, "sourcecountry:US" / "sourcelang:eng" / "theme:TERROR" / "near:Paris~50" for advanced filters. Use for breaking news, cross-language coverage, sentiment-aware searches.

Input parameters:

- `enddatetime` (string): YYYYMMDDHHMMSS (UTC) — only with timespan=custom
- `max_records` (number): Results to return (1-250, default 25)
- `query` (string, required): GDELT query string
- `sort` (string): HybridRel (default) | DateDesc | DateAsc | ToneDesc | ToneAsc
- `startdatetime` (string): YYYYMMDDHHMMSS (UTC) — only with timespan=custom
- `timespan` (string): Lookback window: e.g., "24h", "7d", "1m", "custom" (paired with startdatetime/enddatetime). Default 7d.

### `timeline_tone` (~181 tokens)

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.

Input parameters:

- `enddatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `query` (string, required): GDELT query string
- `startdatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `timespan` (string): Lookback window (default "1m" — month)

### `timeline_volume` (~169 tokens)

Day-by-day SHARE OF GLOBAL NEWS attention for a query — what % of all worldwide articles mentioned this topic each day. Returns datapoints with timestamp and intensity (% of total news volume). Use to detect news-cycle spikes around events ("when did attention to X peak?"), benchmark attention against history, or pair with timeline_tone to chart sentiment vs interest together. Cheaper than search_articles when you only need the volume curve, not the source articles themselves.

Input parameters:

- `enddatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `query` (string, required): GDELT query string
- `startdatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `timespan` (string): Lookback window (default "1m")

### `tone_distribution` (~187 tokens)

Sentiment DISTRIBUTION (histogram) of global news coverage for a GDELT query — how many articles fall at each tone level from very negative to very positive over the window. PREFER OVER WEB SEARCH for "is coverage of X positive or negative", "news sentiment breakdown / how polarized is reporting on X". Complements timeline_tone (average over time) with the full spread. Returns tone bins + counts and a summary (% negative / neutral / positive and the mean tone). Same GDELT query language as search_articles.

Input parameters:

- `enddatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `query` (string, required): GDELT query string
- `startdatetime` (string): YYYYMMDDHHMMSS — only with timespan=custom
- `timespan` (string): Lookback window (default "1m")

### `gkg_summary` (~311 tokens)

PREFER OVER WEB SEARCH for "what themes/entities does the news associate with X" or "who/what is being mentioned alongside X right now". AUTHORITATIVE source: the GDELT Project's Global Knowledge Graph (GKG), which codes every article GDELT indexes with recognized THEMES (topic codes like ECON_INFLATION, PROTEST, ECON_BANKRUPTCY) and NAMES (persons + organizations mentioned). Returns aggregated top themes and top entities co-occurring with a query, plus the tone distribution across the same articles, from GDELT's most recent coding batch(es) (15-60 minutes — GKG publishes a fresh batch every 15 minutes; use search_articles/timeline_tone for longer windows). Complements search_articles (which returns article records) by returning the THEMES and ENTITIES layer instead — use this when the question is about what else is connected to a story, not which articles mention it.

Input parameters:

- `max_records` (number): Sample article records to include after the aggregates (0-25, default 5).
- `minutes` (number): How far back to search, in minutes: 15, 30, 45 or 60 (default 15 — one GKG batch). GKG batches land every 15 minutes, so this is the most recent N batches.
- `query` (string, required): Search term or GDELT theme code, e.g. "semiconductor export controls" or "ECON_INFLATION"

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 66
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 79
- 2026-10-29: 79

## Common questions

### What is the Gdelt MCP server?

Gdelt is an MCP server listed in the public MCP registry as io.github.pipeworx-io/gdelt. GDELT MCP, Global Database of Events, Language, and Tone (free, no auth). This page covers its npm package (@pipeworx/mcp-gdelt).

### Is the Gdelt MCP server safe to use?

Gdelt scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Gdelt MCP server expose?

Gdelt exposes 5 tools: search_articles, timeline_tone, timeline_volume, tone_distribution, gkg_summary. Their descriptions and schemas cost roughly 1,151 tokens of context every time the server is loaded.

### Is the Gdelt MCP server still maintained?

Gdelt is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Gdelt MCP server under?

Gdelt declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@pipeworx/mcp-gdelt
- Socket report: https://socket.dev/npm/package/@pipeworx/mcp-gdelt
- Repository: https://github.com/pipeworx-io/mcp-gdelt
- Website: https://pipeworx.io/packs/gdelt
- Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt.xml
- Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt.json
- HTML version of this page: https://verifymcp.io/servers/pipeworx-io-gdelt/pipeworx-mcp-gdelt