# mcp

Connects Contraption Company essay content to your AI client through search and retrieval tools, using a hosted endpoint or local setup.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 1
- Author: philipithomas
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/philipithomas/ghost-mcp
- Updated: 2026-02-26
- HTML: https://affpapa.org/en/nevibecode/mcp/philipithomas-mcp

## What it does

This server links your AI client to Contraption Company essays indexed inside Chroma Cloud. It exposes three core tools: `search` to run text queries across articles, `list_posts` to paginate through items, and `fetch` to retrieve full markdown content by canonical URL.

Users can connect instantly to the public hosted instance at `https://mcp.contraption.co` without authentication. For local deployments via Python or Docker, you need a Ghost Admin API key, Chroma Cloud database credentials, and a Voyage API key for embeddings.

Query logging and members-only indexing stay active by default.

## Requirements
- Remote server: `https://mcp.contraption.co/`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport sse mcp https://mcp.contraption.co/
```

### Codex

**Codex**
- Codex connects MCP servers over stdio and streamable HTTP only, and this server speaks SSE

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "philipithomas-mcp": {
            "url": "https://mcp.contraption.co/"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "philipithomas-mcp": {
            "type": "sse",
            "url": "https://mcp.contraption.co/"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t sse philipithomas-mcp https://mcp.contraption.co/
```

## When to use it
- search blog posts and pages using text queries
- retrieve complete article text via its canonical identifier
- paginate through published blog posts in chat
- sync updated or newly published Ghost articles every 5 minutes

## Example prompts
- Find blog articles about agents using `search`
- List recent publications with `list_posts`
- Fetch the full content of an essay using `fetch`

## 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

## Other versions with the same name
- [mcp · kubeshark](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — ★ 12110
- [mcp · butterbase-ai](https://affpapa.org/en/nevibecode/mcp/butterbase-ai-mcp.md) — ★ 3031
- [mcp · medplum](https://affpapa.org/en/nevibecode/mcp/mcp.md) — ★ 2766
- [mcp · sceneview](https://affpapa.org/en/nevibecode/mcp/sceneview-mcp.md) — ★ 1349
- [mcp · buoy-gg](https://affpapa.org/en/nevibecode/mcp/buoy-gg-mcp.md) — ★ 691

---
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