Korture Hiring MCP
Transforms job descriptions into behavioral measurement briefs with evidence-based behavioral dimensions and interview questions.
README
Korture Hiring MCP
Korture Hiring is a remote MCP server that turns a job description into a behavioural measurement brief. Paste a JD into Claude, ChatGPT, Cursor, or any MCP-compatible client, and get back the five behaviours that actually matter for the role, the evidence each was picked from, demand levels from 1 to 5, and interview questions tied to every behaviour.
Most AI hiring tools rewrite your JD or guess at "culture fit". This one does not. It is built on Korture Science, evidence-tied, anti-horoscope, every number traceable. The brief tells you what to measure, why, and how to test for it on the call.
It also does the thing your AI assistant cannot do alone. It runs a population reality check against the labour market and tells you how rare this hire actually is, and whether you will find them. If you are searching for a unicorn, you find out before you post.
Free to use with a Korture account. Sign in at korture.com to get a key.
Endpoint: https://mcp.korture.com/api/mcp
Available tools
| Tool | Purpose |
|---|---|
validate_jd |
Confirm the JD has enough signal to analyse. Always call this before create_brief. |
create_brief |
Turn the JD plus three sharpening answers into a behavioural measurement brief: 5 behaviours, evidence per behaviour, demand levels (1 to 5), interview questions. |
enrich_brief |
Add depth to an existing brief: dynamic dimension profiles and a population reality check. |
get_brief |
Retrieve a previously generated brief by id. |
get_dimensions |
List the 15 behavioural dimensions Korture can measure. |
get_external_population_check |
Stratified reality check against a 145k-person external pool, filtered by country, education, and age band. |
get_stats |
Aggregate stats about the public Korture corpus. |
What happens after you have a brief
The brief lives at https://hire.korture.com/brief/{brief_id}. Every
create_brief, enrich_brief, and get_brief response includes a
next_steps block with that link plus a link to the candidates page, where
you add candidates, copy each assess link, and send it to the person.
Candidates complete the assessment, results appear back on the brief page.
The MCP tools cover the brief side of the journey. The send-to-candidates and
review-results steps live on korture.com, which is where the rest of the
work happens.
Connecting from Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"korture-hiring": {
"url": "https://mcp.korture.com/api/mcp"
}
}
}
Quit Claude Desktop fully and reopen. The connector appears in your tray.
First time you connect
The connector requires a Korture account. After you add it, Claude Desktop
shows a Connect button on its connectors page. Click it. You will be
sent to hire.korture.com to authenticate via email OTP, no password.
Authentication takes about 20 seconds.
Once you finish, return to Claude Desktop. All seven tools become available. Your account is remembered until you revoke it from the connectors page.
After you have a brief
Every successful create_brief, enrich_brief, and get_brief response
includes a next_steps block with two URLs:
next_steps.view_brief— the brief on korture.comnext_steps.add_candidates— the page where you add candidates and copy per-candidate scan links to send
Claude will surface these to you at the end of the response. Open them in your browser to continue the workflow.
If you previously connected to https://korture-mcp-server.vercel.app/api/mcp,
update the URL above and re-authenticate. The old URL still serves traffic via
a redirect, but the canonical address from now on is mcp.korture.com.
Connecting from Cursor (one click)
Click the button above in a browser that has Cursor installed. Cursor opens with the server name and URL pre-filled, you confirm and save.
Connecting from ChatGPT and other MCP clients
Any MCP client that supports remote Streamable HTTP servers will work with the
same URL: https://mcp.korture.com/api/mcp. ChatGPT desktop and the official
ChatGPT app directory entry both use this address.
Authentication
The server participates in OAuth 2.1 with PKCE (RFC 6749 + 7636, per the MCP spec). It advertises:
https://mcp.korture.com/.well-known/oauth-protected-resource— resource metadata (RFC 9728)https://hire.korture.com/.well-known/oauth-authorization-server— authorization server metadata (RFC 8414)- Dynamic Client Registration at
https://hire.korture.com/api/oauth/register(RFC 7591)
MCP clients that implement DCR register themselves automatically. For service-to-service callers, an internal-tier API key is available on request.
Rate limits are tier-based. Internal and admin tiers are unlimited; the free tier is 10 briefs per day. The MCP server does not accept unauthenticated calls.
Source and deployment
- Code:
api/mcp.ts, a thin stateless wrapper aroundhire.korture.com/api/v1/* - Runtime: Vercel Functions (Streamable HTTP transport, no session id required)
- License: Apache-2.0
The MCP server contains no scoring logic, no prompts, and no dimension definitions. All behavioural analysis happens upstream in the Korture core system, so this repo is safe to fork or audit publicly.
Contributing
Issues and PRs welcome. For security disclosures, email
security@korture.com rather than opening a public issue.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.