# Outlit

Feeds your agent live customer data: churn risk, expansion signals, items worth a human look. Useful when support and revenue ride on long-tail accounts.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: OutlitAI
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/OutlitAI/outlit-sdk
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/outlit

## What it does

Outlit runs as a hosted remote MCP server. Point an agent at it and it can pull customer context mid-task: which accounts are slipping, where an upsell looks likely, what evidence backs each signal.

The endpoint is `https://mcp.outlit.ai/mcp`, over HTTP. Claude takes one line — `claude mcp add --transport http outlit https://mcp.outlit.ai/mcp`. Codex uses `codex mcp add outlit --url https://mcp.outlit.ai/mcp`. Cursor and GitHub Copilot expect the same URL as an HTTP entry in their config files. Access goes through OAuth with a workspace URL, so an Outlit workspace is required before anything comes back.

The public packages live in `OutlitAI/outlit-sdk`: `@outlit/browser`, `@outlit/node`, `@outlit/core`, `@outlit/cli`, `@outlit/tools`, `@outlit/pi`, plus a Rust crate. They cover sending signals and querying context. The MCP server itself is not in that repo — it sits on `mcp.outlit.ai`.

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

## Install

### Claude Code (native platform)

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

### Codex

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

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

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

## When to use it
- surface accounts at churn risk inside the agent chat
- spot customers ready to move up a plan
- gather supporting evidence before a call on a troubled account
- send product events from a Node.js backend
- query customer context from an agent workflow

## Example prompts
- List accounts with churn risk this month
- Which customers look ready to expand, and why?
- Pull context for account `cust_123`

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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