MCP Server Template for Cloudflare Workers
by jezweb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUTH_TOKEN | No | Optional Bearer token for programmatic authentication | |
| ADMIN_EMAILS | No | Comma-separated list of admin email addresses | |
| CF_AIG_TOKEN | No | Cloudflare AI Gateway token for authenticated gateway and BYOK | |
| OPENAI_API_KEY | No | Optional OpenAI API key for AI chat testing | |
| GITHUB_CLIENT_ID | No | Optional GitHub OAuth Client ID | |
| GOOGLE_CLIENT_ID | Yes | Google OAuth Client ID for authentication | |
| ANTHROPIC_API_KEY | No | Optional Anthropic API key for AI chat testing | |
| BETTER_AUTH_SECRET | Yes | Secret key for better-auth session encryption (32-byte hex string) | |
| MICROSOFT_CLIENT_ID | No | Optional Microsoft Entra OAuth Client ID | |
| GITHUB_CLIENT_SECRET | No | Optional GitHub OAuth Client Secret | |
| GOOGLE_CLIENT_SECRET | Yes | Google OAuth Client Secret for authentication | |
| INTERNAL_AGENT_MODEL | No | Workers AI model to use for internal agent gatekeeper | @cf/qwen/qwen2.5-coder-32b-instruct |
| MAX_CONTEXT_MESSAGES | No | Maximum number of messages to load for context | 50 |
| COOKIE_ENCRYPTION_KEY | Yes | Secret key for cookie encryption for approved clients (32-byte hex string) | |
| ENABLE_INTERNAL_AGENT | No | Enable ask_agent tool with Workers AI gatekeeper for voice agents | false |
| CONVERSATION_TTL_HOURS | No | Auto-delete conversations after specified hours (default: 7 days) | 168 |
| MICROSOFT_CLIENT_SECRET | No | Optional Microsoft Entra OAuth Client Secret | |
| ENABLE_CONVERSATION_MEMORY | No | Enable D1-backed conversation memory for persistent chat history | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jezweb/google-calendar-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server