Contraption Company MCP
Provides semantic search and access to Contraption Company blog posts and essays. Uses AI-powered embeddings to find relevant content and supports real-time updates via webhooks.
README
Contraption Company MCP
An MCP (Model Context Protocol) server for Contraption Company essay, built on Chroma Cloud.
How to Install
Contraption Company MCP is available as a hosted MCP server with no authentication.
| Field | Value |
|---|---|
| Server URL | https://mcp.contraption.co |
How to configure in common clients
<details> <summary><b>Cursor</b></summary>
Create or edit ~/.cursor/mcp.json:
{
"mcpServers": {
"contraption-company": {
"url": "https://mcp.contraption.co"
}
}
}
</details>
<details> <summary><b>VS Code (Copilot Chat MCP)</b></summary>
Create or edit .vscode/mcp.json:
{
"servers": {
"contraption-company": {
"type": "http",
"url": "https://mcp.contraption.co"
}
}
}
</details>
<details> <summary><b>Codex</b></summary>
Add to ~/.codex/config.toml:
[mcp_servers.contraption-company]
command = "npx"
args = ["mcp-remote", "--transport", "http", "https://mcp.contraption.co"]
</details>
<details> <summary><b>Claude Code</b></summary>
Run in your terminal:
claude mcp add --transport http contraption-company https://mcp.contraption.co
</details>
<details> <summary><b>OpenAI SDK (Python)</b></summary>
from openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5",
input="List the newest Contraption Company blog posts.",
tools=[
{
"type": "mcp",
"server_label": "contraption-company",
"server_url": "https://mcp.contraption.co",
"require_approval": "never",
}
],
)
print(response)
</details>
Features
- Semantic Search: Uses Qwen3-Embedding-0.6B model for efficient semantic search
- Automatic Indexing: Syncs with blog API on startup and via webhooks
- Full Content Access: Uses Ghost Admin API to index all published content including members-only posts
- Fast Performance: Powered by FastAPI and Chroma Cloud
- Real-time Updates: Webhook support for instant post updates
- Docker Ready: Includes Dockerfile for easy deployment
- Well Tested: Comprehensive test suite with pytest
Run Locally
- Clone and install:
git clone <repository>
cd mcp
uv sync --all-extras
- Configure environment:
cp .env.example .env
# Edit .env with your credentials
- Run the server:
./run.sh
# Or: uv run python -m src.main
Docker
# Build
docker build -t contraption-mcp .
# Run
docker run -p 8000:8000 --env-file .env contraption-mcp
# Or use docker-compose
docker-compose up
Configuration
Running locally requires credentials for external services:
- Ghost Admin API Key: From your Ghost Admin panel (Settings > Integrations)
- Chroma Cloud Credentials: Tenant ID, Database, and API key from Chroma Cloud
- Ghost Blog URL: Your Ghost blog's URL
MCP Tools
get_post(slug): Get a single blog post by sluglist_posts(sort_by, page, limit): List posts with paginationsearch_posts(query, limit): Semantic search across posts
API Endpoints
GET /: Server info (redirects to GitHub repo for non-MCP requests)GET /health: Health checkPOST /webhook/ghost/{secret}: Secure webhook endpoint for Ghost updates/mcp/*: MCP protocol endpoints
Webhook Security
The webhook endpoint requires a secret token in the URL path for security. Configure it in Ghost Admin:
- Go to Settings → Integrations → Webhooks
- Set URL to:
https://your-domain.com/webhook/ghost/{your-webhook-secret} - Replace
{your-webhook-secret}with the value from your.envfile - Select events: Post published, Post updated, Post deleted
Development
# Install dev dependencies
make dev
# Run tests
make test
# Lint and format
make format lint
# Run all checks
make check
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。