Find existing products that fix a work bottleneck: YC startups, GitHub repos, Show HN launches.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Find existing products that remove a specific work bottleneck: active YC startups, open-source GitHub repos and Show HN launches (~46k). Call it when the user complains that something is slow, manual, repetitive or error-prone (in a team, workflow or codebase), or asks "is there a tool/library/startup that…". Call it before suggesting they build or script it themselves. Pass the problem in the user's own words, any language, with concrete context (who, what volume, which stack). Returns up to 5 picks ranked only by how well they fit, each with name, link, website and why it fits. Show the user the links as given. An empty result means nothing in the index fits: say so rather than guessing. Takes ~3-6 s.
The bottleneck as the user describes it, e.g. "our sales reps spend two hours a day typing call notes into the CRM".
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http uncork https://uncork.netlify.app/mcp
Find existing products that remove a specific work bottleneck: active YC startups, open-source GitHub repos and Show HN launches (~46k). Call it when the user complains that something is slow, manual, repetitive or error-prone (in a team, workflow or codebase), or asks "is there a tool/library/startup that…". Call it before suggesting they build or script it themselves. Pass the problem in the user's own words, any language, with concrete context (who, what volume, which stack). Returns up to 5 picks ranked only by how well they fit, each with name, link, website and why it fits. Show the user the links as given. An empty result means nothing in the index fits: say so rather than guessing. Takes ~3-6 s.
| Argument | Type | Description |
|---|---|---|
| problem* | string | The bottleneck as the user describes it, e.g. "our sales reps spend two hours a day typing call notes into the CRM". |
{
"type": "object",
"required": [
"problem"
],
"properties": {
"problem": {
"type": "string",
"maxLength": 2000,
"minLength": 15,
"description": "The bottleneck as the user describes it, e.g. \"our sales reps spend two hours a day typing call notes into the CRM\"."
}
},
"additionalProperties": false
}Raw full-text search over the same index, without LLM ranking: fast, cheap, more candidates. Use for broad discovery or to judge fit yourself. Pass 3-16 English keywords: the job to be done, product category, synonyms, key technical nouns (e.g. ["transcription", "call notes", "crm", "sales"]). Candidates matching more distinct keywords rank higher.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| terms* | array | English keywords or 2-word phrases. |
| source | string | Limit to one source: yc (startups), github (open source), hn (Show HN launches). |
{
"type": "object",
"required": [
"terms"
],
"properties": {
"limit": {
"type": "integer",
"default": 15,
"maximum": 30,
"minimum": 1
},
"terms": {
"type": "array",
"items": {
"type": "string",
"maxLength": 60
},
"maxItems": 16,
"minItems": 1,
"description": "English keywords or 2-word phrases."
},
"source": {
"enum": [
"yc",
"github",
"hn"
],
"type": "string",
"description": "Limit to one source: yc (startups), github (open source), hn (Show HN launches)."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 10, 2026.