Access Agent Interviews Data via MCP
MCP server exposing Agent Interviews hiring data - interviews, transcripts, reports, projects - to Claude and Cursor via a prefixed, key-authenticated tool set.
Why it matters
Integrate your AI assistants with the Agent Interviews platform to access and analyze technical assessment data. Streamline your recruiting process by querying interview details, transcripts, and project information directly.
Outcomes
What it gets done
List all available projects within Agent Interviews.
Retrieve specific interview details and transcripts.
Access information about interviewers.
Securely authenticate with the Agent Interviews API using your provided key.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-agent-interviews | bash Capabilities
Tools your agent gets
List all projects in your Agent Interviews account
Get details of a specific interview
List all interviewers in your Agent Interviews account
Get interview transcript
Overview
Agent Interviews MCP Server
An MCP server that connects Claude and Cursor to Agent Interviews, an AI interview-as-a-service platform for technical hiring. It exposes interview, transcript, project, and interviewer data through API-key-authenticated tools prefixed agentinterviews_. Use it when a hiring team wants to query interview status, pull transcripts, or check interviewer and project details directly from an AI assistant instead of the Agent Interviews dashboard.
What it does
This MCP server connects Claude, Cursor, and other MCP-compatible AI assistants to Agent Interviews, an AI interview-as-a-service platform that lets companies deploy customizable AI interviewers tailored to specific roles and skills, run consistent and bias-reduced technical interviews at scale, and evaluate candidates through natural conversation. The platform itself produces detailed reports and structured candidate-performance data meant to integrate with an existing hiring workflow; this MCP server is the bridge that lets that data be queried from inside an AI assistant. Rather than switching to the Agent Interviews dashboard, the assistant can query interview status, retrieve transcripts and reports, and look up interviewer and project details directly, using natural-language questions that the assistant maps to the right underlying tool.
When to use - and when NOT to
Use it when a hiring team or engineer already has an Agent Interviews account and wants that data available inside an AI workflow - checking on recent interviews, pulling a transcript for a specific candidate, or listing which interviewers and projects exist. It is a read-oriented data connector, not the interview platform itself: it does not create AI interviewers, run interviews, or evaluate candidates - those actions happen in Agent Interviews directly, and this server only surfaces the results. It also requires an active Agent Interviews account and API key, so it is not usable standalone.
Capabilities
All tools are namespaced with an agentinterviews_ prefix to avoid colliding with other MCP servers in the same client. Documented tools include agentinterviews_list_projects (list all projects), agentinterviews_get_interview (details on a specific interview), agentinterviews_list_interviewers (list configured AI interviewers), and agentinterviews_get_transcript (pull a transcript from a completed interview). Example natural-language queries the source shows working out of the box: checking the status of recent interviews, retrieving a specific candidate's transcript, listing available projects, and pulling details about a named interviewer.
How to install
Requires an Agent Interviews account with API access and an MCP-compatible client. The same configuration pattern works for both Cursor and Claude Desktop:
{
"mcpServers": {
"agentinterviews": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.agentinterviews.com/mcp",
"--header",
"Authorization:${API_KEY}"
],
"env": {
"API_KEY": "Api-Key YOUR_API_KEY_HERE"
}
}
}
}
The API key authenticates every request and should never be shared or committed to a public repository; the source stresses this as its main security note, since the key is the only thing gating access to interview data. Setup guides for both clients are maintained in the Agent Interviews documentation, and support is available by email or through the project's issue tracker if the connection or a specific tool call misbehaves.
Who it's for
Technical recruiters and hiring managers who use Agent Interviews for AI-run technical assessments and want interview status, transcripts, and reports surfaced inside Claude or Cursor instead of a separate dashboard tab. The project is licensed under MIT.
Source README
Agent Interviews MCP
Access your Agent Interviews data directly from Claude and Cursor using Model Context Protocol (MCP)
What is Agent Interviews?
Agent Interviews is a cutting-edge AI interview-as-a-service platform that helps companies streamline their technical assessment process. Our platform allows you to:
- Create AI interviewers tailored to specific roles and skills
- Conduct consistent, bias-reduced technical interviews at scale
- Collect structured data on candidate performance
- Save engineering time while maintaining high hiring standards
With Agent Interviews, you can deploy customizable AI interviewers that evaluate candidates through natural conversation, provide detailed reports, and integrate with your existing hiring workflow.
Overview
The Agent Interviews MCP server provides a standardized way for AI assistants to access your interview data, reports, and transcripts using the Model Context Protocol (MCP). This integration allows Claude, Cursor, and other MCP-compatible AI assistants to seamlessly interact with your Agent Interviews account.
Features
- ✅ Secure API Access: Connect to your Agent Interviews account using your API key
- ✅ Prefixed Tools: All tools use the
agentinterviews_prefix to avoid collisions with other MCPs - ✅ Comprehensive Functionality: Access interviews, transcripts, reports, projects, and more
- ✅ Intuitive Queries: Ask natural language questions and let the AI determine the right tools to use
Documentation
For comprehensive setup guides and usage instructions, visit our official documentation:
Quick Start
Prerequisites
- An Agent Interviews account with API access
- Your Agent Interviews API key
- MCP-compatible client (Claude Desktop, Cursor, etc.)
Cursor Setup
{
"mcpServers": {
"AgentInterviews": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.agentinterviews.com/mcp",
"--header",
"Authorization:${API_KEY}"
],
"env": {
"API_KEY": "Api-Key YOUR_API_KEY_HERE"
}
}
}
}
Claude Desktop Setup
Edit your Claude Desktop config file (accessible via Claude menu → Settings → Developer → Edit Config):
{
"mcpServers": {
"agentinterviews": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.agentinterviews.com/mcp",
"--header",
"Authorization:${API_KEY}"
],
"env": {
"API_KEY": "Api-Key YOUR_API_KEY_HERE"
}
}
}
}
Example Usage
Once configured, you can ask questions like:
- "Show me the status of my recent interviews"
- "Get the transcript from my last interview with candidate John Smith"
- "What projects do I have available?"
- "Show me details about the 'Senior Developer' interviewer"
Available Tools
Our MCP server exposes tools with the agentinterviews_ prefix. Some key tools include:
agentinterviews_list_projects: List all your projectsagentinterviews_get_interview: Get details about a specific interviewagentinterviews_list_interviewers: List all your interviewersagentinterviews_get_transcript: Get a transcript from an interview
Security
The Agent Interviews MCP server requires your API key for authentication. This key is used to securely access your account data. Never share your API key or include it in public repositories.
Related Projects
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.