Overview
Keyword Extractor works by analyzing the text and extracting the keywords based on their frequency. It uses advanced algorithms to extract the keywords and returns the keywords in a structured format.
Live Test Keyword Extraction Skill Skill →
The tool
Once your client is connected to the VerveKit server, this appears in its tool list as KeywordExtractionSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.
{
"name": "KeywordExtractionSkill",
"arguments": {
"text": "Machine learning is a subset of artificial intelligence that enables systems to learn from data. Deep learning uses neural networks to process complex patterns in data."
}
}You do not name the tool yourself; the model picks it. Asking about Machine learning is a subset of artificial intelligence that enables systems to learn from data. Deep learning uses neural networks to process complex patterns in data. in the terms this skill covers is enough for it to reach for KeywordExtractionSkill on its own — naming it explicitly also works, and is the way to force the call.
Connecting
One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.
{
"mcpServers": {
"vervekit": {
"url": "https://api.vervekit.com/v1/mcp"
}
}
}https://api.vervekit.com/v1/mcpPer-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.
| Argument | Type | Description |
|---|---|---|
textRequired | string | The text to extract keywords from length 0–50000 |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"url": "https://en.wikipedia.org/wiki/Email_address",
"keywordCount": 50,
"topKeyword": "email",
"totalOccurrences": 672,
"keywords": {
"email": 94,
"address": 61,
"mail": 52,
"domain": 34,
"addresses": 34,
"characters": 27,
"retrieved": 27,
"internet": 17,
"message": 15,
"validation": 12
},
"topKeywords": [
{
"keyword": "email",
"count": 94,
"percentage": 14
},
{
"keyword": "address",
"count": 61,
"percentage": 9.1
},
{
"keyword": "mail",
"count": 52,
"percentage": 7.7
},
{
"keyword": "domain",
"count": 34,
"percentage": 5.1
},
{
"keyword": "addresses",
"count": 34,
"percentage": 5.1
}
]
}
}
Response fields
Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.
| Field | Type | Example | Description |
|---|---|---|---|
url | string | https://en.wikipedia.org/wiki/Email_address | The web page URL that was provided and scraped for keyword extraction |
keywordCount | number | 50 | Number of unique keywords returned, capped at 50 |
topKeyword | string | email | The most frequently occurring keyword |
totalOccurrences | number | 672 | Total sum of all keyword frequencies |
keywords | object | {…} | Map of each extracted keyword to the number of times it occurred in the page text |
keywords.email | number | 94 | |
keywords.address | number | 61 | |
keywords.mail | number | 52 | |
keywords.domain | number | 34 | |
keywords.addresses | number | 34 | |
keywords.characters | number | 27 | |
keywords.retrieved | number | 27 | |
keywords.internet | number | 17 | |
keywords.message | number | 15 | |
keywords.validation | number | 12 | |
topKeywords | array[5] | Top 5 keywords with counts and percentages | |
topKeywords.0.keyword | string | email | The keyword |
topKeywords.0.count | number | 94 | How many times the keyword occurs |
topKeywords.0.percentage | number | 14 | The keyword's share of all keyword occurrences, as a percentage |
Failure modes
Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.
| Status | What it means |
|---|---|
400 / 422 | The arguments did not validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Blocked by a key restriction or an IP allow-list. Never a bad identity. |
404 | This skill is not part of VerveKit. Check the catalog. |
429 | Out of credits, or a brief rate limit. The message tells them apart. |
A call costs 10 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Competitor Webpage Audit
- SEO specialists submit competitor article URLs to see top keyword density and discover which subjects competitors focus on.
- Editorial CMS Tagging
- When editors draft articles, publishing systems read the returned top terms to auto-suggest relevant tags and taxonomy categories before publication.
- Support Ticket Categorization
- Classify high-volume helpdesk requests automatically by mapping recurring keywords and frequency counts from incoming ticket text to triage queues.
- Ad Copy Term Analysis
- Marketing teams check landing pages against prospective ad copy to align top keyword frequencies with targeted search ad campaigns.
Other ways to use Keyword Extraction Skill
Set up Keyword Extraction Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.
Related
More in Text Processing: