damonzucconi-mcp
Enables managing the site's API via natural language, with tools for artworks, exhibitions, tags, nested entities, and ordering, while protecting the endpoint with a bearer token and caching admin JWT. It supports Cursor and ChatGPT desktop clients, with cloud deployment via Cloudflare Workers.
README
damonzucconi-mcp
Remote MCP server for managing damonzucconi.com through its GraphQL API.
Production endpoint: https://damonzucconi-mcp.damonzucconi.workers.dev/mcp
The server is one stateless Cloudflare Worker with no storage bindings. A static bearer token protects the MCP endpoint. The Worker signs into the GraphQL API with the existing admin credentials and caches the resulting JWT until shortly before expiry.
It exposes tools for artworks, exhibitions, tags, nested entities, and ordering. Artwork and exhibition deletion are intentionally unavailable; perform those manually.
Local development
Requires Node.js 20+ and npm.
npm install
cp .dev.vars.example .dev.vars
Set the three secrets in .dev.vars:
openssl rand -hex 32
MCP_AUTH_TOKEN=<paste-generated-value>
ADMIN_USERNAME=your-api-admin-username
ADMIN_PASSWORD=your-api-admin-password
MCP_AUTH_TOKEN is a shared secret, not a username or login token. The Worker stores one copy and each MCP client sends the same value as a bearer token. Possession of this value grants access to the server.
There is no automatic synchronization:
.dev.varssupplies the local Worker and is the source used bynpm run secrets:push.npm run secrets:pushcopies the value to Cloudflare's encrypted Worker secrets for production.- Cursor and ChatGPT read that same value from the client-side environment variable
DAMONZUCCONI_MCP_TOKEN.
If you change MCP_AUTH_TOKEN, run npm run secrets:push, update DAMONZUCCONI_MCP_TOKEN, and restart the client. A client using a different value will receive 401 Unauthorized.
npm run codegen
npm run typecheck
npm run dev
The local MCP endpoint is http://127.0.0.1:8787/mcp. In another terminal:
npm run smoke
To test production instead:
MCP_URL=https://damonzucconi-mcp.damonzucconi.workers.dev npm run smoke
Connect from Cursor
Add this to .cursor/mcp.json for this project or ~/.cursor/mcp.json globally:
{
"mcpServers": {
"damonzucconi": {
"url": "https://damonzucconi-mcp.damonzucconi.workers.dev/mcp",
"headers": {
"Authorization": "Bearer ${env:DAMONZUCCONI_MCP_TOKEN}"
}
}
}
}
Set DAMONZUCCONI_MCP_TOKEN in the environment Cursor inherits, using the same value as MCP_AUTH_TOKEN in .dev.vars, then restart Cursor. Remote servers do not support envFile.
Connect from ChatGPT desktop
The ChatGPT desktop app shares MCP configuration with Codex in ~/.codex/config.toml. Add:
[mcp_servers.damonzucconi]
url = "https://damonzucconi-mcp.damonzucconi.workers.dev/mcp"
bearer_token_env_var = "DAMONZUCCONI_MCP_TOKEN"
default_tools_approval_mode = "writes"
On macOS, make the token available to apps launched from Finder or the Dock:
read -s "DAMONZUCCONI_MCP_TOKEN?MCP token: "
echo
launchctl setenv DAMONZUCCONI_MCP_TOKEN "$DAMONZUCCONI_MCP_TOKEN"
unset DAMONZUCCONI_MCP_TOKEN
Paste the same value as MCP_AUTH_TOKEN when prompted by read. The token is not written to config.toml or shell history.
Fully quit and reopen ChatGPT, then open Settings → MCP servers and select Restart. Type /mcp in the composer to confirm that damonzucconi is connected. See OpenAI's MCP documentation if the desktop UI changes.
Deploy
Wrangler authentication opens a browser:
npx wrangler login
For a first deployment:
npm run deploy
npm run secrets:push
secrets:push uploads the three entries from .dev.vars. On later deployments, run only npm run deploy unless a secret changed.
Before deploying changes:
npm run codegen
npm run typecheck
npm run smoke
npm run deploy
MCP_URL=https://damonzucconi-mcp.damonzucconi.workers.dev npm run smoke
GraphQL code generation
Queries and mutations live in src/graphql/. npm run codegen introspects the live API and refreshes:
schema.graphqlsrc/generated/
Do not edit generated files. If codegen or type checking fails after an API change, update the .graphql operations or their Zod tool schemas before deploying.
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.