# io.github.cyanheads/gdelt-mcp-server

> Search and analyze global news coverage and US TV transcripts via the GDELT Project APIs.

- name: io.github.cyanheads/gdelt-mcp-server
- version: 0.7.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgdelt-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgdelt-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "gdelt-mcp-server": {
      "type": "http",
      "url": "https://gdelt.caseyjhand.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% +updated-6d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 5 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 9 of 9 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: gdelt_search_articles (destructiveHint, idempotentHint); gdelt_get_tone_distribution (destructiveHint, idempotentHint); gdelt_get_coverage_breakdown (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 6,372 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 18 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 74 resolved packages
- pass `deps.mcp_sdk_version`: @modelcontextprotocol/core 2.3.1, no known advisory
- pass `deps.resolvable`: @cyanheads/gdelt-mcp-server@0.7.0, @cyanheads/gdelt-mcp-server@0.7.0 resolved: 74 packages

- tools: 9, about 6,372 tokens to load them all
- tool set hash: c9d50c004653e487254e0994bde7dddf
- tools last changed: 2026-10-14T23:59:23.913Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.cyanheads/gdelt-mcp-server.svg)](https://protogrid.dev/servers/io.github.cyanheads/gdelt-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-14 `gdelt_get_tv_context` changed (description, outputSchema)
  - before: Get the top co-occurring words and phrases from TV news clips matching a query — the vocabulary framing a topic on television. Returns the most frequent non-stopword terms from matching clips, with relative frequency scores (0–100, where 100 = the query term itself). Use to understand narrative framing, identify related concepts mentioned alongside a topic, or generate follow-up search terms. TV data spans 2009–October 2024.
  - after: Get the top co-occurring words and phrases from TV news clips matching a query — the vocabulary framing a topic on television. Returns the most frequent non-stopword terms with relative frequency scores (0–100, where 100 = the query term itself). Terms and scores come from GDELT's relevance-ranked sample of matching clips, documented as the 200 most relevant, not all matching coverage — compare windows or stations with a separate, narrower call for each. Use to understand narrative framing, identify related concepts mentioned alongside a topic, or generate follow-up search terms. TV data spans 2009–October 2024.
- 2026-10-14 `gdelt_get_tv_clips` changed (description, inputSchema, outputSchema)
  - before: Retrieve the top matching TV news clips for a query from the Internet Archive's Television News Archive: fetches up to 3,000 and returns as many as fit a 48,000-byte response — the rest are counted in withheldCount, with a continuation to reach them. Each clip includes show name, station, air timestamp, a 15-second transcript excerpt, and a direct link to view the full one-minute clip. Use after gdelt_search_tv to read the actual transcript content driving a coverage spike. GDELT answers TV windows in whole clock hours; clips it returns from outside an explicit startDatetime/endDatetime window are dropped, and continuing a cut response at maxRecords 3000 leaves room for them. 3,000 is a hard per-call ceiling and GDELT offers no cursor: when a query fills it or a response comes back cut, re-query narrower startDatetime/endDatetime windows — the response hands back the exact windows to use. Archive coverage spans 2009–October 2024.
  - after: Retrieve the top matching TV news clips for a query from the Internet Archive's Television News Archive: fetches up to 3,000 and returns as many as fit a 48,000-byte response — the rest are counted in withheldCount, with a continuation to reach them. Each clip includes show name, the station's display name — with its station ID when that name resolves to one — air timestamp, a 15-second transcript excerpt, and a direct link to view the full one-minute clip. Use after gdelt_search_tv to read the actual transcript content driving a coverage spike — pass a series' station value as stations here. GDELT answers TV windows in whole clock hours; clips it returns from outside an explicit startDatetime/endDatetime window are dropped, and continuing a cut response at maxRecords 3000 leaves room for them. 3,000 is a hard per-call ceiling and GDELT offers no cursor: when a query fills it or a response comes back cut, re-query narrower startDatetime/endDatetime windows — the response hands back the exact windows to use. Archive coverage spans 2009–October 2024.
- 2026-10-14 `gdelt_search_tv` changed (description, inputSchema, outputSchema)
  - before: Search US television news closed captions (2009–October 2024, 150+ stations) for spoken mentions of a query. Returns a bounded, paged per-station time series showing airtime devoted to the topic. Use the stations parameter to select networks (e.g. ["CNN", "FOXNEWS", "MSNBC"]) — the TV API requires at least one station, supplied either there or as a station: selector inside query. TV query also supports in-query operators: station:CNN, network:CBS, market:"National", show:"Anderson Cooper 360", context:"vaccine". Important: most station monitoring ended October 2024 — use gdelt_list_tv_stations to verify active date ranges before querying recent events.
  - after: Search US television news closed captions (2009–October 2024, 150+ stations) for spoken mentions of a query. Returns a bounded, paged per-station time series showing airtime devoted to the topic — up to 500 points per page; a larger limit runs at 500. Each series carries GDELT's display name for the station and, when that name resolves to one, the station ID gdelt_get_tv_clips takes as stations. Use the stations parameter to select networks (e.g. ["CNN", "FOXNEWS", "MSNBC"]) — the TV API requires at least one station, supplied either there or as a station: selector inside query. TV query also supports in-query operators: station:CNN, network:CBS, market:"National", show:"Anderson Cooper 360", context:"vaccine". Important: most station monitoring ended October 2024 — use gdelt_list_tv_stations to verify active date ranges before querying recent events.
- 2026-10-14 `gdelt_search_themes` changed (description, inputSchema, outputSchema)
  - before: Find GDELT Global Knowledge Graph (GKG) theme identifiers for the theme: operator that gdelt_search_articles, gdelt_get_coverage_timeline, gdelt_get_tone_distribution, and gdelt_get_coverage_breakdown accept in query. Searches the identifiers in the GDELT GKG theme lookup, which carries no labels or descriptions: every query word must begin one of the _-separated parts of an identifier or run across consecutive parts, or all the words joined must, so "drought" finds NATURAL_DISASTER_DROUGHT, "cyberattack" finds CYBER_ATTACK, "plant disease" finds TAX_PLANTDISEASE, and "wb water" narrows to World Bank water themes. There is no stemming or synonym matching — "displacement" does not reach DISPLACED — except one fallback: when nothing matches, the search retries once with a trailing s dropped from each word of four or more letters, and says so. Matches rank an exact identifier first, then by the count the lookup lists — a static prevalence figure, not a live article total — and each carries a paste-ready operator such as theme:TAX_DISEASE_OUTBREAK. Page with offset and limit.
  - after: Find GDELT Global Knowledge Graph (GKG) theme identifiers for the theme: operator that gdelt_search_articles, gdelt_get_coverage_timeline, gdelt_get_tone_distribution, and gdelt_get_coverage_breakdown accept in query. Searches the identifiers in the GDELT GKG theme lookup, which carries no labels or descriptions: every query word must begin one of the _-separated parts of an identifier or run across consecutive parts, or all the words joined must, so "drought" finds NATURAL_DISASTER_DROUGHT, "cyberattack" finds CYBER_ATTACK, "plant disease" finds TAX_PLANTDISEASE, and "wb water" narrows to World Bank water themes. There is no stemming or synonym matching — "displacement" does not reach DISPLACED — except one fallback: when nothing matches, the search retries once with a trailing s dropped from each word of four or more letters, and says so. Matches rank an exact identifier first, then by the count the lookup lists — a static prevalence figure, not a live article total — and each carries a paste-ready operator such as theme:TAX_DISEASE_OUTBREAK. Page with offset and limit (up to 100 matches per page; a larger limit runs at 100).
- 2026-10-14 `gdelt_get_coverage_breakdown` changed (description, inputSchema, outputSchema)
  - before: Break down news coverage volume over time by source language or source country, returning a multi-series time series (one series per language or country). Shows which countries or languages drove early vs. late coverage — useful for tracing how a story propagated geographically or across language communities. Returns up to 10 series by total volume and aggregates the rest into an "Other" bucket, naming every series it folded in there under otherSeriesLabels — pass any of those labels back as the series input to get that series complete, ranked or not. Values are normalized: each point is the topic's share of media output, not an absolute article count. Small media markets with concentrated coverage therefore rank above large markets with diverse output — a high value means the topic dominated that source's coverage, not that it published the most articles. Use breakdownBy "country" with the signal-detection chain to map geographic attention, or "language" to detect non-English media surges.
  - after: Break down news coverage volume over time by source language or source country, returning a multi-series time series (one series per language or country). Shows which countries or languages drove early vs. late coverage — useful for tracing how a story propagated geographically or across language communities. Returns the top 10 series ranked by the sum of their values and names every other series under otherSeriesLabels — pass any labels, ranked or not, as the series input to get only those series, complete. A response carries as many whole series as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Values are normalized: each point is the topic's share of that source's media output, not an absolute article count, so values from different sources do not add up to a share. Small media markets with concentrated coverage therefore rank above large markets with diverse output — a high value means the topic dominated that source's coverage, not that it published the most articles. Use breakdownBy "country" with the signal-detection chain to map geographic attention, or "language" to detect non-English media surges.
- 2026-10-14 `gdelt_get_tone_distribution` changed (description, inputSchema, outputSchema)
  - before: Get the tonal distribution of articles matching a query as a histogram (bins approximately -30 to +30). Unlike a single average tone score, the histogram reveals whether coverage is uniformly negative, bimodal (some articles extremely positive and some extremely negative), or clustered near neutral. Each bin includes representative article URLs. Distinct from gdelt_get_coverage_timeline (mode: tone) — this is a snapshot distribution across all matching articles, not a time series. Use gdelt_get_coverage_timeline with mode "tone" to see how sentiment shifted over time.
  - after: Get the tonal distribution of articles matching a query as a histogram (bins approximately -30 to +30). Unlike a single average tone score, the histogram reveals whether coverage is uniformly negative, bimodal (some articles extremely positive and some extremely negative), or clustered near neutral. Each bin carries its first 3 representative article links and referenceCount, how many GDELT returned; name bins in the bins input to get only those bins, each with every link. A response carries as many whole bins as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Distinct from gdelt_get_coverage_timeline (mode: tone) — this is a snapshot distribution across all matching articles, not a time series. Use gdelt_get_coverage_timeline with mode "tone" to see how sentiment shifted over time.
- 2026-10-14 `gdelt_get_coverage_timeline` changed (description, inputSchema, outputSchema)
  - before: Retrieve a time series showing when news coverage of a topic spiked, or how average tone shifted over time. Use mode "volume" for normalized coverage intensity (% of all global coverage per timestep). Use mode "volume_with_articles" for the same signal plus the top articles that drove each spike — this is the primary signal-detection mode: a single call reveals both the spike and its cause, avoiding a follow-up gdelt_search_articles call. Use mode "tone" for average sentiment score per timestep (negative = hostile/fearful, positive = celebratory). Date resolution is inferred from returned intervals: 15 minutes or hours for short windows, days for longer ones. In volume_with_articles mode the text surface shows the first 3 article links per timestep next to that timestep's true article count; name a timestep's date in points to render its full list. Note: DOC API covers only the last 3 months.
  - after: Retrieve a time series showing when news coverage of a topic spiked, or how average tone shifted over time. Use mode "volume" for normalized coverage intensity (% of all global coverage per timestep). Use mode "volume_with_articles" for the same signal plus the top articles that drove each spike — this is the primary signal-detection mode: a single call reveals both the spike and its cause, avoiding a follow-up gdelt_search_articles call. Use mode "tone" for average sentiment score per timestep (negative = hostile/fearful, positive = celebratory). Date resolution is inferred from returned intervals: 15 minutes or hours for short windows, days for longer ones. In volume_with_articles mode each timestep carries its first 3 article links and referenceCount, its true article count; name timesteps' dates in points to get only those timesteps, each with its full list. A response carries as many whole timesteps as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Note: DOC API covers only the last 3 months.
- 2026-10-14 `gdelt_search_articles` changed (inputSchema, outputSchema)
- 2026-09-24 `gdelt_get_tv_trending` removed
  - Retrieve trending topics, keywords, and phrases currently dominating US television news across national networks. No query required — returns the top memes of the present news cycle. Updated every 15 minutes. Note: the GDELT TV archive feed stopped updating around October 2024; results from this endpoint reflect that most-recent archived data rather than a live feed.
- 2026-09-24 `gdelt_list_tv_stations` changed (description, inputSchema, outputSchema, annotations)
  - before: List all television stations available for TV search with their market, network, monitoring start date, and monitoring end date. Stations with an end date within the last 24 hours are flagged as active; stations with earlier end dates are discontinued. Use before querying to verify a station was active during the target time period, or to discover valid station IDs for the stations parameter in other TV tools. Most station monitoring ended October 2024 when the Internet Archive TV feed stopped updating.
  - after: List the television stations available for TV search with their market, network, monitoring start date, and monitoring end date — every station by default, or only those matching the optional stations, network, and market filters (each an exact, case-insensitive match; combined with AND). activeCount and totalCount count the returned stations. Stations with an end date within the last 24 hours are flagged as active; stations with earlier end dates are discontinued. Use before querying to verify a station was active during the target time period, or to discover valid station IDs for the stations parameter in other TV tools. Most station monitoring ended October 2024 when the Internet Archive TV feed stopped updating.

Full history: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgdelt-mcp-server/changes

## Dependencies

- npm @cyanheads/gdelt-mcp-server@0.7.0: resolved, 36 dependencies, MCP SDK @modelcontextprotocol/core 2.3.1
- npm @cyanheads/gdelt-mcp-server@0.7.0: resolved, 36 dependencies, MCP SDK @modelcontextprotocol/core 2.3.1

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://gdelt.caseyjhand.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm @cyanheads/gdelt-mcp-server@0.7.0
- npm @cyanheads/gdelt-mcp-server@0.7.0

## Tools (9)

- `gdelt_get_coverage_breakdown`: Break down news coverage volume over time by source language or source country, returning a multi-series time series (one series per language or country). Shows which countries or languages drove early vs. late coverage — useful for tracing how a story propagated geographically or across language communities. Returns the top 10 series ranked by the sum of their values and names every other series under otherSeriesLabels — pass any labels, ranked or not, as the series input to get only those series, complete. A response carries as many whole series as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Values are normalized: each point is the topic's share of that source's media output, not an absolute article count, so values from different sources do not add up to a share. Small media markets with concentrated coverage therefore rank above large markets with diverse output — a high value means the topic dominated that source's coverage, not that it published the most articles. Use breakdownBy "country" with the signal-detection chain to map geographic attention, or "language" to detect non-English media surges.
- `gdelt_get_coverage_timeline`: Retrieve a time series showing when news coverage of a topic spiked, or how average tone shifted over time. Use mode "volume" for normalized coverage intensity (% of all global coverage per timestep). Use mode "volume_with_articles" for the same signal plus the top articles that drove each spike — this is the primary signal-detection mode: a single call reveals both the spike and its cause, avoiding a follow-up gdelt_search_articles call. Use mode "tone" for average sentiment score per timestep (negative = hostile/fearful, positive = celebratory). Date resolution is inferred from returned intervals: 15 minutes or hours for short windows, days for longer ones. In volume_with_articles mode each timestep carries its first 3 article links and referenceCount, its true article count; name timesteps' dates in points to get only those timesteps, each with its full list. A response carries as many whole timesteps as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Note: DOC API covers only the last 3 months.
- `gdelt_get_tone_distribution`: Get the tonal distribution of articles matching a query as a histogram (bins approximately -30 to +30). Unlike a single average tone score, the histogram reveals whether coverage is uniformly negative, bimodal (some articles extremely positive and some extremely negative), or clustered near neutral. Each bin carries its first 3 representative article links and referenceCount, how many GDELT returned; name bins in the bins input to get only those bins, each with every link. A response carries as many whole bins as fit its size budget; when more remain it returns nextOffset — pass it back as offset with otherwise identical inputs for the next page. Distinct from gdelt_get_coverage_timeline (mode: tone) — this is a snapshot distribution across all matching articles, not a time series. Use gdelt_get_coverage_timeline with mode "tone" to see how sentiment shifted over time.
- `gdelt_get_tv_clips`: Retrieve the top matching TV news clips for a query from the Internet Archive's Television News Archive: fetches up to 3,000 and returns as many as fit a 48,000-byte response — the rest are counted in withheldCount, with a continuation to reach them. Each clip includes show name, the station's display name — with its station ID when that name resolves to one — air timestamp, a 15-second transcript excerpt, and a direct link to view the full one-minute clip. Use after gdelt_search_tv to read the actual transcript content driving a coverage spike — pass a series' station value as stations here. GDELT answers TV windows in whole clock hours; clips it returns from outside an explicit startDatetime/endDatetime window are dropped, and continuing a cut response at maxRecords 3000 leaves room for them. 3,000 is a hard per-call ceiling and GDELT offers no cursor: when a query fills it or a response comes back cut, re-query narrower startDatetime/endDatetime windows — the response hands back the exact windows to use. Archive coverage spans 2009–October 2024.
- `gdelt_get_tv_context`: Get the top co-occurring words and phrases from TV news clips matching a query — the vocabulary framing a topic on television. Returns the most frequent non-stopword terms with relative frequency scores (0–100, where 100 = the query term itself). Terms and scores come from GDELT's relevance-ranked sample of matching clips, documented as the 200 most relevant, not all matching coverage — compare windows or stations with a separate, narrower call for each. Use to understand narrative framing, identify related concepts mentioned alongside a topic, or generate follow-up search terms. TV data spans 2009–October 2024.
- `gdelt_list_tv_stations`: List the television stations available for TV search with their market, network, monitoring start date, and monitoring end date — every station by default, or only those matching the optional stations, network, and market filters (each an exact, case-insensitive match; combined with AND). activeCount and totalCount count the returned stations. Stations with an end date within the last 24 hours are flagged as active; stations with earlier end dates are discontinued. Use before querying to verify a station was active during the target time period, or to discover valid station IDs for the stations parameter in other TV tools. Most station monitoring ended October 2024 when the Internet Archive TV feed stopped updating.
- `gdelt_search_articles`: Search the last 3 months of global news coverage (65+ languages) using the GDELT DOC API. Fetches up to 250 articles with URL, title, source domain, language, country, publication date, and social image URL, and returns as many as fit a 48,000-byte response — the rest are counted in withheldCount, with a continuation to reach them. Query supports full GDELT syntax: phrases ("bird flu"), boolean OR ((flu OR pandemic)), source country (sourcecountry:china), source language (sourcelang:spanish), domain (domain:who.int), GKG theme (theme:TAX_DISEASE_OUTBREAK — find identifiers with gdelt_search_themes), tone filter (tone<-5 for negative), proximity (near20:"flu virus"), and repeat (repeat3:"outbreak"). 250 is a hard per-call ceiling and GDELT offers no cursor: when a query fills it or a response comes back cut, re-query narrower startDatetime/endDatetime windows — the response hands back the exact windows to use. Note: this API covers only the most recent 3 months — use gdelt_search_tv for historical TV transcripts back to 2009.
- `gdelt_search_themes`: Find GDELT Global Knowledge Graph (GKG) theme identifiers for the theme: operator that gdelt_search_articles, gdelt_get_coverage_timeline, gdelt_get_tone_distribution, and gdelt_get_coverage_breakdown accept in query. Searches the identifiers in the GDELT GKG theme lookup, which carries no labels or descriptions: every query word must begin one of the _-separated parts of an identifier or run across consecutive parts, or all the words joined must, so "drought" finds NATURAL_DISASTER_DROUGHT, "cyberattack" finds CYBER_ATTACK, "plant disease" finds TAX_PLANTDISEASE, and "wb water" narrows to World Bank water themes. There is no stemming or synonym matching — "displacement" does not reach DISPLACED — except one fallback: when nothing matches, the search retries once with a trailing s dropped from each word of four or more letters, and says so. Matches rank an exact identifier first, then by the count the lookup lists — a static prevalence figure, not a live article total — and each carries a paste-ready operator such as theme:TAX_DISEASE_OUTBREAK. Page with offset and limit (up to 100 matches per page; a larger limit runs at 100).
- `gdelt_search_tv`: Search US television news closed captions (2009–October 2024, 150+ stations) for spoken mentions of a query. Returns a bounded, paged per-station time series showing airtime devoted to the topic — up to 500 points per page; a larger limit runs at 500. Each series carries GDELT's display name for the station and, when that name resolves to one, the station ID gdelt_get_tv_clips takes as stations. Use the stations parameter to select networks (e.g. ["CNN", "FOXNEWS", "MSNBC"]) — the TV API requires at least one station, supplied either there or as a station: selector inside query. TV query also supports in-query operators: station:CNN, network:CBS, market:"National", show:"Anderson Cooper 360", context:"vaccine". Important: most station monitoring ended October 2024 — use gdelt_list_tv_stations to verify active date ranges before querying recent events.