# Calven

Calven gives an AI agent access to approved product, buyer, and competitor context. Use it to review drafts or prepare for deals using your team’s materials.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: calven-ai
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/calven-ai/calven-mcp
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/calven

## What it does

The MCP server exposes product positioning, buyer messaging, ICP details, personas, competitor materials, and win/loss information. Answers include sources. Access to CRM accounts and deals depends on workspace settings.

Calven provides read tools and a `review_against_personas` action that starts a persona-based review. The server does not search the web, and its instructions tell the model not to fill missing details from its own knowledge. Its tools do not change workspace content or publish and send material.

You need a Calven workspace and OAuth sign-in. In Claude Code, add the server with `claude mcp add --transport http calven https://api.calven.ai/mcp`, then authenticate in the browser. Each person’s access follows their Calven role. Company information may be confidential.

## Requirements
- Remote server: `https://api.calven.ai/mcp`

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- check product claims against approved team materials
- prepare questions for a deal involving a competitor
- review a draft against buyer personas
- trace lost deals to customer evidence

## Example prompts
- Compare the product and competitor claims in this draft with our approved materials.
- Review our lost deals and suggest a question for the next customer conversation.
- Check this copy against our personas and revise claims that do not fit buyer evidence.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
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