John Deere Operations Center MCP Server
Enables interaction with the John Deere Operations Center to browse organizations, field details, and agricultural operation data. It utilizes a Cloudflare Workers architecture with an integrated OAuth proxy for secure access via any MCP-compatible client.
README
John Deere Operations Center MCP Server
A remote MCP server hosted on Cloudflare Workers that connects to John Deere Operations Center. Browse organizations, fields, and field operations data via any MCP-compatible client (Claude Desktop, Cursor, etc.).
Architecture
The server runs as a Cloudflare Worker with a Durable Object (McpAgent) providing stateful MCP sessions. Authentication uses a double OAuth proxy pattern:
- Downstream: The Worker is an OAuth server to MCP clients
- Upstream: The Worker is an OAuth client to John Deere
This means authentication happens at the transport layer — no manual auth tool call is needed.
Setup
1. Cloudflare Account & Wrangler CLI
-
Create a Cloudflare account (if you don’t have one):
- Go to dash.cloudflare.com/sign-up and sign up.
- Verify your email and complete account setup.
-
Install the Wrangler CLI (Cloudflare’s Workers CLI):
npm install -g wranglerOr use it via
npx(no global install):npx wrangler --version -
Log in to Cloudflare from the terminal:
npx wrangler loginThis opens a browser to authenticate Wrangler with your Cloudflare account.
2. Register a John Deere Developer Application
- Go to developer.deere.com and sign in.
- Create a new application under My Applications.
- Add your Worker's callback URL as a Redirect URI:
https://john-deere-mcp.<your-subdomain>.workers.dev/callback - Copy your Application ID (Client ID) and Secret (Client Secret).
3. Create the KV Namespace
npx wrangler kv namespace create OAUTH_KV
Copy the output id into wrangler.jsonc under kv_namespaces.
4. Set Secrets
npx wrangler secret put JD_CLIENT_ID
npx wrangler secret put JD_CLIENT_SECRET
npx wrangler secret put COOKIE_ENCRYPTION_KEY
For local development, copy .dev.vars.example to .dev.vars and fill in the values.
5. Install & Deploy
npm install
npm run deploy
6. Connect an MCP Client
Add to your client's MCP config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"john-deere": {
"command": "npx",
"args": ["mcp-remote", "https://john-deere-mcp.<your-subdomain>.workers.dev/mcp"]
}
}
}
Tools
| Tool | Description |
|---|---|
jd_list_organizations |
Lists all accessible organizations |
jd_list_fields |
Lists fields for an organization |
jd_get_field |
Gets field details including boundaries |
jd_list_field_operations |
Lists planting/harvest/application operations |
Commands
| Command | Description |
|---|---|
/jd-fields [org] |
Browse fields in an organization |
/jd-ops [field] |
View field operations data |
Local Development
cp .dev.vars.example .dev.vars
# Fill in JD_CLIENT_ID, JD_CLIENT_SECRET, COOKIE_ENCRYPTION_KEY
npm run dev
Test with the MCP Inspector:
npx @modelcontextprotocol/inspector@latest
Connect to http://localhost:8787/mcp.
Transport Type: Streamable HTTP Connection Type: Direct
Environment
This targets the John Deere Sandbox (sandboxapi.deere.com). Sandbox limits:
- Max 5 connected organizations
- Max 150,000 API calls/month
- 18-month maximum sandbox duration
For production access, apply through the John Deere developer portal.
Required OAuth Scopes
ag1 ag2 ag3 eq1 eq2 org1 org2 files offline_access
These are requested automatically during the OAuth flow.
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.