Y Combinator Companies Search API and MCP — Filter by Batch, Industry, Region and Team Size
Send a keyword and any of the filters (batches, industries, regions, team size range, hiring, top company, nonprofit) and get matching companies back as JSON: name, link, one-liner, description, batch, status, stage, team size, industries, regions, tags, location, website, hiring flag and launch date. Sort by relevance or newest first.
- You send
- an optional keyword and filters (batches, industries, regions, team size range, hiring, top company, nonprofit, sort order) plus a max_items cap (up to 250)
- You get back
- matching companies with one-liner, batch, status, industries, regions, team size and website
- Coverage
- Y Combinator records with a public page.
- Price
- 1 point per returned record — $1 per 1,000
- Billed per record actually returned, capped by max_items. A request that returns nothing costs nothing.
Ways to get this data
Three approaches teams use today, and where each one runs into trouble.
| Approach | What it takes | Cost | Trade-off |
|---|---|---|---|
| Y Combinator directly | Type the query into Y Combinator and read the results | Free, and slow | Fine for one record, useless across a list, and the layout differs on every platform |
| Building a scraper | Write it, host it, and repair it when Y Combinator changes its pages | Engineering time | A maintenance commitment for something that isn't your product |
| NeuralVerge | One request, the same shape as every other source in the catalog | $1 per 1,000, misses not billed | Returns what Y Combinator publishes at request time. Other platforms are separate sources with the same request format |
What you get back
Every field in the example response below.
| Field | Type | Description |
|---|---|---|
session_id | string | Id of this run, for tracing. |
kind | string | Source type of the response. |
max_items | number | The cap on returned records, as run. |
start_page | number | Page the run started from. |
partial | boolean | True when the run stopped before reaching max_items. |
human | string | Readable summary: the query, how many results came back and how many were found. |
total_points | number | Points charged for the run. |
machine.total_items | number | Number of companies returned in this response. |
machine.total_found | number | Total matches reported by the platform, when it reports one. |
machine.first_item.id | string | Company slug. |
machine.first_item.name | string | Company name. |
machine.first_item.url | string | Link to the company page. |
machine.first_item.alias | string | Slug as the directory uses it. |
machine.first_item.yc_id | number | Numeric company id. |
machine.first_item.one_liner | string | One-line description. |
machine.first_item.description | string | Longer description. Shortened in the sample. |
machine.first_item.batch | string | Batch, e.g. Summer 2013. |
machine.first_item.status | string | Company status, e.g. Public. |
machine.first_item.stage | string | Stage as listed, e.g. Growth. |
machine.first_item.team_size | number | Team size as listed. |
machine.first_item.industry | string | Top-level industry. |
machine.first_item.subindustry | string | Industry and sub-industry. |
machine.first_item.industries | array | Industry list. |
machine.first_item.regions | array | Region list. |
machine.first_item.tags | array | Tags. |
machine.first_item.location | string | Location as listed. |
machine.first_item.website | string | Company website. |
machine.first_item.logo | string | Logo URL. |
machine.first_item.former_names | array | Earlier names. Empty in the sample. |
machine.first_item.is_hiring | boolean | Whether the company is marked as hiring. |
machine.first_item.top_company | boolean | Whether the company is marked as a top company. |
machine.first_item.nonprofit | boolean | Whether the company is a nonprofit. |
machine.first_item.launched_at | string | Launch date (YYYY-MM-DD). |
machine.items[] | array | Companies returned, same shape as first_item. |
machine.page_count | number | Pages read for the run. |
machine.blocked | boolean | Whether the platform refused the request. |
machine.proxy_traffic_bytes | number | Size of the data transferred for the run, in bytes. |
Example response
A real response, as returned.
{
"session_id": "11111111-1111-1111-1111-111111111111",
"kind": "yc_companies_search",
"max_items": 2,
"start_page": 1,
"partial": false,
"human": "# Y Combinator — companies search\n\n- **Query:** max_items=2\n- **Results:** 2 of 6283 found\n- **Proxy traffic:** 7.0 KB",
"machine": {
"total_items": 2,
"first_item": {
"id": "doordash",
"name": "DoorDash",
"url": "https://www.ycombinator.com/companies/doordash",
"alias": "doordash",
"yc_id": 531,
"one_liner": "Restaurant delivery.",
"description": "Founded in 2013, DoorDash is a San Francisco-based technology company passionate about transforming local businesses and dedicated to enabling new ways of working, earning, and living. Today, DoorDash",
"batch": "Summer 2013",
"status": "Public",
"stage": "Growth",
"team_size": 8600,
"industry": "Consumer",
"subindustry": "Consumer -> Food and Beverage",
"industries": [
"Consumer",
"Food and Beverage"
],
"regions": [
"United States of America",
"America / Canada"
],
"tags": [
"Marketplace",
"E-commerce"
],
"location": "San Francisco, CA, USA",
"website": "http://doordash.com",
"logo": "https://bookface-images.s3.amazonaws.com/small_logos/d13287c52acc96909f32342e85c26a33cfdac310.png",
"former_names": [],
"is_hiring": true,
"top_company": true,
"nonprofit": false,
"launched_at": "2013-05-02"
},
"items": [
{
"id": "doordash",
"name": "DoorDash",
"url": "https://www.ycombinator.com/companies/doordash",
"alias": "doordash",
"yc_id": 531,
"one_liner": "Restaurant delivery.",
"description": "Founded in 2013, DoorDash is a San Francisco-based technology company passionate about transforming local businesses and dedicated to enabling new ways of working, earning, and living. Today, DoorDash",
"batch": "Summer 2013",
"status": "Public",
"stage": "Growth",
"team_size": 8600,
"industry": "Consumer",
"subindustry": "Consumer -> Food and Beverage",
"industries": [
"Consumer",
"Food and Beverage"
],
"regions": [
"United States of America",
"America / Canada"
],
"tags": [
"Marketplace",
"E-commerce"
],
"location": "San Francisco, CA, USA",
"website": "http://doordash.com",
"logo": "https://bookface-images.s3.amazonaws.com/small_logos/d13287c52acc96909f32342e85c26a33cfdac310.png",
"former_names": [],
"is_hiring": true,
"top_company": true,
"nonprofit": false,
"launched_at": "2013-05-02"
},
{
"id": "airbnb",
"name": "Airbnb",
"url": "https://www.ycombinator.com/companies/airbnb",
"alias": "airbnb",
"yc_id": 271,
"one_liner": "Book accommodations around the world.",
"description": "Founded in August of 2008 and based in San Francisco, California, Airbnb is a trusted community marketplace for people to list, discover, and book unique accommodations around the world — online or fr",
"batch": "Winter 2009",
"status": "Public",
"stage": "Growth",
"team_size": 6132,
"industry": "Consumer",
"subindustry": "Consumer -> Travel, Leisure and Tourism",
"industries": [
"Consumer",
"Travel, Leisure and Tourism"
],
"regions": [
"United States of America",
"America / Canada"
],
"tags": [
"Marketplace",
"Travel"
],
"location": "San Francisco, CA, USA",
"website": "http://airbnb.com",
"logo": "https://bookface-images.s3.amazonaws.com/small_logos/3e9a0092bee2ccf926e650e59c06503ec6b9ee65.png",
"former_names": [],
"is_hiring": false,
"top_company": true,
"nonprofit": false,
"launched_at": "2012-01-17"
}
],
"total_found": 6283,
"page_count": 1,
"blocked": false,
"proxy_traffic_bytes": 7212
},
"total_points": 2
}How to run it
The same lookup works from the app, the API, or as a tool an agent can call mid-task.
Results come back in the same envelope as every other source: a session id, a readable summary, the structured result and the points charged. max_items caps how many records are returned and billed.
curl -X POST https://api.neuralverge.ai/functions/v1/run-yc-companies-search \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"max_items":2}'What teams use it for
Where this field shows up in an actual workflow.
Pull every company in a batch or set of batches for research or outreach lists.
Filter by industry and region, such as Fintech in Europe, and read size and status.
Filter to companies marked as hiring, within a team size range.
Coverage, freshness and limits
What this source covers, how fresh it is, and where it stops.
Y Combinator records with a public page.
Read at request time, so the answer reflects the platform as it stands when you ask.
This source returns information Y Combinator shows publicly. Every response carries the session id you can trace.
- —Filters are applied by the directory; the source does not add its own scoring or de-duplication.
- —The directory does not give funding amounts or valuations.
- —Results are capped by max_items (up to 250); use start_page to continue past the first page.
Questions, answered
Send them comma-separated, for example "Winter 2024, Summer 2024".
Related sources
Try y combinator companies search on your own data
One request format across every source in the catalog.