# InterviewFlowAI

Hosted MCP server linking your InterviewFlowAI workspace to AI assistants to query candidate profiles and review interview evaluations.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2 repo stars
- Author: interviewflowai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/interviewflowai/interviewflowai-mcp
- Updated: 2026-09-11
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/interviewflowai

## What it does

This remote service operates at `https://api.interviewflowai.com/mcp` using the Streamable HTTP transport. Nothing runs locally. The client discovers tools and completes OAuth 2.1 authentication in the browser using your existing InterviewFlowAI account. The assistant never gets broader access than your personal profile holds.

Under the `mcp:read` scope, the model retrieves applicant lists, inspects interview scores, and summarizes discussion logs. Modifying candidate notes or archived flags requires the `mcp:write` scope, restricted strictly to workspace Owners. The server does not automate hiring decisions or change pipeline stages automatically. It only extracts and organizes workspace data so people can make informed choices.

## Requirements
- Remote server: `https://api.interviewflowai.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://api.interviewflowai.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add interviewflowai --url https://api.interviewflowai.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "interviewflowai": {
            "url": "https://api.interviewflowai.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "interviewflowai": {
            "type": "http",
            "url": "https://api.interviewflowai.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http interviewflowai https://api.interviewflowai.com/mcp
```

## When to use it
- find applicants with interview scores meeting a specific cutoff
- summarize interview notes without reviewing entire transcripts
- update candidate notes and custom attributes from the chat window
- evaluate finalists side by side on specific skill areas

## Example prompts
- Show candidates who completed their interview with a score of 70 or higher.
- Compare the top two candidates on communication skills and draft a debrief summary.
- Update the notes for this candidate with feedback from our team review.

## Similar
- [evaluating-candidates](https://affpapa.org/en/nevibecode/skills/evaluating-candidates.md) — skill · 1 install
- [interview-system-designer](https://affpapa.org/en/nevibecode/skills/interview-system-designer.md) — skill · 672 installs
- [Clera](https://affpapa.org/en/nevibecode/mcp/clera.md) — MCP server · ★ 10 repo stars
- [hr-automation](https://affpapa.org/en/nevibecode/skills/hr-automation.md) — skill · 5100 installs
- [recruiting-pipeline](https://affpapa.org/en/nevibecode/skills/recruiting-pipeline.md) — skill · 3100 installs
- [talent-acquisition](https://affpapa.org/en/nevibecode/skills/talent-acquisition.md) — skill · 348 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
