Startup Jobs
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
claude mcp add --transport http startup-jobs 'https://api.startup.jobs/mcp' --header 'Authorization: <Optional. Bearer sj_… API key from https://startup.jobs/account/api_keys for usage attribution and full access. Free tier works without a key. Docs: https://startup.jobs/mcp>'{
"mcpServers": {
"startup-jobs": {
"type": "http",
"url": "https://api.startup.jobs/mcp",
"headers": {
"Authorization": "<Optional. Bearer sj_… API key from https://startup.jobs/account/api_keys for usage attribution and full access. Free tier works without a key. Docs: https://startup.jobs/mcp>"
}
}
}
}Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Startup Jobs MCP Server
Search live startup.jobs listings from Claude, Cursor, ChatGPT, or any Model Context Protocol client.
Docs: https://startup.jobs/mcp
Endpoint (Streamable HTTP): https://api.startup.jobs/mcp
Smithery: https://smithery.ai/servers/jobs/startup-jobs
Official Registry: io.github.killbridge/startupjobs-mcp
This repository is the public listing + registry package for the hosted MCP server. The server itself runs on startup.jobs (not in this repo).
What you get
- Search startup jobs (keyword, role, country, remote / hybrid / on-site, employment type)
- Full job details and company profiles
- Hiring trends and salary benchmarks from listings that disclose pay
- Free anonymous access (recent listings); optional API key for attribution / full archive
Connect
Claude Code
claude mcp add --transport http startup-jobs https://api.startup.jobs/mcpCursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"startup-jobs": {
"url": "https://api.startup.jobs/mcp"
}
}
}Claude / ChatGPT
Paste https://api.startup.jobs/mcp as a custom connector. No authentication required for the free tier.
Optional API key
Create a free key at https://startup.jobs/account/api_keys and send it as:
Authorization: Bearer sj_...or (for gateways that reserve Authorization):
X-Api-Key: sj_...Tools
| Tool | Description |
|---|---|
search_jobs | Search live listings with filters |
get_job | Full job description + apply URL |
get_company | Company profile and live listing count |
get_company_jobs | All live listings for one company |
list_roles | Role taxonomy for filters |
list_countries | Countries with jobs |
job_trends | Posting volume over time |
salary_benchmarks | Salary percentiles from disclosed pay |
Example prompts
- Find remote senior Rails jobs at startups posted this week
- What are Series B fintech companies hiring for in Europe?
- Salary percentiles for product designer roles in the US
- Show hiring trends for AI engineer roles over the last year
Related
- REST API: https://startup.jobs/api
- Product: https://startup.jobs
License
MIT — see LICENSE. The job data remains © Killbridge / startup.jobs; this repo covers the MCP listing materials and registry metadata.
Frequently asked questions
What is Startup Jobs?
Search live startup jobs from Claude, Cursor, or ChatGPT via MCP. Free, no account needed.
How do I install Startup Jobs?
It runs as a remote server. In Claude Code: claude mcp add --transport http startup-jobs 'https://api.startup.jobs/mcp' --header 'Authorization: <Optional. Bearer sj_… API key from https://startup.jobs/account/api_keys for usage attribution and full access. Free tier works without a key. Docs: https://startup.jobs/mcp>'. For other clients, paste the JSON configuration from this page into their MCP settings.
Does Startup Jobs need an API key?
Yes. It expects Authorization, which you set in its configuration.
Is Startup Jobs open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains Startup Jobs?
It is published by killbridge. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.