Crawlora MCP

Official

Overview Schema Source Related Servers Discussions Admin

gdelt_tv_search

Search US TV news transcripts, captions, OCR text, and visual labels via GDELT's Television 2.0 index. Filter by station, show, or time window to find broadcast clips.

Instructions

Search US television news coverage (transcripts, captions, OCR, visual labels). Search GDELT's Television 2.0 AI index of US television news.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	No	End of an absolute time window. Same formats as from.
`from`	No	Start of an absolute time window. Accepts YYYY-MM-DD, RFC3339, or GDELT's raw YYYYMMDDHHMMSS. Cannot be combined with timespan.
`show`	No	Limit to an exact show name.
`sort`	No	Result order.
`visual`	No	Search visual object/activity labels from computer vision (GDELT's visual: operator). Repeatable; multiple values are OR'd together.
`caption`	No	Search human-provided closed captioning (GDELT's cap: operator). Repeatable; multiple values are OR'd together.
`concept`	No	Search Google Knowledge Graph concepts extracted from captioning, by MID code (GDELT's capnlp: operator). Repeatable; multiple values are OR'd together.
`station`	Yes	Station to search.
`timespan`	No	Relative time window ending now, e.g. 1h, 7d, 3m, 1y. Cannot be combined with from/to. GDELT's TV archive starts July 6, 2010.
`maxrecords`	No	Rows to return. GDELT's own hard cap is 3000 for this endpoint; there is no pagination cursor beyond it.
`transcript`	No	Search machine-generated speech-to-text transcripts (GDELT's asr: operator). Repeatable; multiple values are OR'd together. Short phrases only (GDELT caps each at 5 words).
`day_of_week`	No	Limit to a day of week, 0 (Sunday) through 7 (Saturday), PST.
`onscreen_text`	No	Search OCR'd onscreen text/chyrons (GDELT's ocr: operator). Repeatable; multiple values are OR'd together. Short phrases only (GDELT caps each at 5 words).
`exclude_visual`	No	Exclude clips whose visual labels match this value (GDELT's -visual: operator). Repeatable; every value must be absent.
`exclude_caption`	No	Exclude clips whose closed captioning matches this value (GDELT's -cap: operator). Repeatable; every value must be absent.
`exclude_concept`	No	Exclude clips whose extracted concepts match this MID code (GDELT's -capnlp: operator). Repeatable; every value must be absent.
`exclude_transcript`	No	Exclude clips whose speech-to-text transcript matches this value (GDELT's -asr: operator). Repeatable; every value must be absent.
`exclude_onscreen_text`	No	Exclude clips whose OCR'd onscreen text matches this value (GDELT's -ocr: operator). Repeatable; every value must be absent.

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv1.17.5Sep 26, 2026
- addedInput schema / properties / caption / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / concept / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / exclude_caption / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / exclude_concept / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / exclude_onscreen_text / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / exclude_transcript / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / exclude_visual / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / onscreen_text / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / sort / enum
```
Added value: +[
+  "relevance",
+  "datedesc",
+  "dateasc"
+]
```
- addedInput schema / properties / station / enum
```
Added value: +[
+  "CNN",
+  "MSNBC",
+  "FOXNEWS",
+  "BBCNEWS",
+  "KGO",
+  "KPIX",
+  "KNTV"
+]
```
- addedInput schema / properties / transcript / items
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / visual / items
```
Added value: +{
+  "type": "string"
+}
```
Addedv1.16.0Aug 29, 2026

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Search' weakly implies a read-only operation, but the description does not disclose result behavior, limits, query semantics, or any other operational traits. The schema carries most of the behavioral weight, but the description itself adds almost none.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded, with no filler. The only minor issue is that the second sentence ('Search GDELT's Television 2.0 AI index of US television news') largely restates the scope already given in the first sentence, so one of the two sentences is somewhat redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex 18-parameter tool with no annotations and no output schema. The schema itself is rich and documents all parameters, which reduces the burden, but the description still fails to cover important contextual facts: what a result looks like, how queries combine across fields, whether station is required beyond the schema, or why an agent might choose this over related GDELT TV tools. The description alone is not enough to invoke the tool confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds a small amount of semantic context by listing the media types (transcripts, captions, OCR, visual labels) that map to the transcript, caption, onscreen_text, and visual parameters, but it does not meaningfully explain any parameter beyond what the schema already documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Search') and resource ('US television news coverage' via GDELT's Television 2.0 index), and enumerates the content types searched: transcripts, captions, OCR, and visual labels. It is clearly about TV-clip search rather than general GDELT article search, but it does not explicitly contrast with sibling TV tools like gdelt_tv_timeline or gdelt_tv_stationdetails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to prefer this tool over alternatives such as gdelt_search, gdelt_tv_timeline, or gdelt_tv_visual_entities. The description states what the tool searches but never says when it is appropriate, when it is not, or which sibling covers other use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

gdelt_tv_search

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools