mcpu

mcpu

MCP server for managing Cloudflare Workers via Cloudflare Artifacts. Enables editing, committing, and deploying worker scripts directly.

Category
Visit Server

README

mcpu

Deploy to Cloudflare

mcpu is an MCP control surface for a Cloudflare Artifacts repo. GitHub is only the bootstrap seed. After first deploy, source commits live in Cloudflare Artifacts and deploy back to Cloudflare Workers.

Start here

1. Deploy to your Cloudflare account

Click Deploy to Cloudflare above and finish the deploy flow.

When it completes, copy your Worker URL. It will look like:

https://mcpu.<your-subdomain>.workers.dev

If you deploy with workers_dev = false, use the route or custom domain you configured instead.

2. Protect /mcp

Before adding deploy-capable secrets, protect /mcp with Cloudflare Access or an equivalent auth layer. Do not expose a public MCP endpoint with ARTIFACTS_TOKEN or CLOUDFLARE_API_TOKEN configured.

3. Add secrets for the Artifact loop

mcpu needs an Artifacts Git remote and token before repo.commit can push source to Cloudflare Artifacts.

Set these Worker secrets/vars in your account:

ARTIFACTS_REMOTE=https://<account-id>.artifacts.cloudflare.net/git/default/mcpu.git
ARTIFACTS_TOKEN=art_v1_...
ARTIFACTS_BRANCH=main
MCPU_SCRIPT_NAME=mcpu
CLOUDFLARE_ACCOUNT_ID=<account-id>
CLOUDFLARE_API_TOKEN=<token that can edit Workers>

GitHub is not used after bootstrap.

4. Add mcpu to your MCP config

Use your deployed Worker URL plus /mcp.

{
  "mcpServers": {
    "mcpu": {
      "url": "https://mcpu.<your-subdomain>.workers.dev/mcp"
    }
  }
}

For a custom domain:

{
  "mcpServers": {
    "mcpu": {
      "url": "https://mcpu.example.com/mcp"
    }
  }
}

5. Try it

Ask your agent:

Connect to mcpu. Run repo.status, list files, read worker.js, change the homepage text, show the diff, commit it, and deploy it.

Expected loop:

repo.write -> repo.diff -> repo.commit -> Cloudflare Artifacts -> repo.deploy -> Cloudflare Workers

Local development

Run the seed locally:

npm install
npm test
npm run dev -- --port 8799

Then connect to:

http://localhost:8799/mcp

Local MCP config:

{
  "mcpServers": {
    "mcpu-local": {
      "url": "http://localhost:8799/mcp"
    }
  }
}

Reference

Tools:

  • repo.status
  • repo.ls
  • repo.read
  • repo.write
  • repo.diff
  • repo.commit
  • repo.deploy
  • repo.history

State:

  • draft - mutable working tree
  • artifact - immutable source commit in Cloudflare Artifacts
  • deployment - Worker version deployed from an Artifact

Explanation

GitHub gets you to zero. Cloudflare owns everything after.

The demo is intentionally tiny: a live MCP edits a Cloudflare Artifacts repo, commits it, and deploys that Artifact as the next version of itself.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured