Maple
by alnosarus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_URL | No | The URL where the MCP server is hosted (e.g., http://localhost:3000). | |
| MAPLE_API_KEY | No | API key for authenticating with the Maple server. Auth is fail-closed by default. | |
| MAPLE_API_KEYS | No | Alternative to MAPLE_API_KEY, allows providing multiple keys. | |
| OPENAI_API_KEY | No | API key for OpenAI to enable AI-powered firewall chat mode. | |
| SLACK_BOT_TOKEN | No | Bot token for the slack_post_message tool (alternative to webhook mode). | |
| ANTHROPIC_API_KEY | No | API key for Anthropic to enable AI-powered firewall chat mode. | |
| DEMO_OPEN_BROWSER | No | Set to '0' to disable auto-opening browser pages during demo:up. | 1 |
| SLACK_WEBHOOK_URL | No | Incoming webhook URL for the slack_post_message tool. | |
| MAPLE_ALLOW_NO_AUTH | No | If set to 'true', allows local-only bypass of API key authentication (not recommended). | |
| OPENCLAW_BRIDGE_URL | No | The URL of the OpenClaw bridge adapter. Required in production. | |
| OPENCLAW_BRIDGE_TOKEN | No | The token used to authenticate with the OpenClaw bridge. Required in production. | |
| SLACK_DEFAULT_CHANNEL | No | Optional default channel for Slack bot mode. | |
| MAPLE_FIREWALL_ENABLED | No | Whether to enable deterministic firewall policy checks (true | false). | true |
| MAPLE_FIREWALL_LOG_DIR | No | Directory for firewall audit logs. | ~/.maple/firewall-logs |
| MAPLE_LOCK_BRIDGE_TARGET | No | Set to 'true' to deny per-request bridgeUrl/token overrides. Enabled automatically in production. | true |
| MAPLE_ALLOW_BRIDGE_OVERRIDE | No | If set to 'true', allows local-only override of the bridge configuration. | |
| MAPLE_FIREWALL_CHAT_PRIMARY | No | Primary model provider for firewall chat (openai | anthropic). | |
| MAPLE_FIREWALL_DEFAULT_ACTION | No | Default firewall behavior (allow | deny | log_only). | allow |
| MAPLE_FIREWALL_CHAT_TIMEOUT_MS | No | Timeout in milliseconds for firewall chat AI responses. | 15000 |
| MAPLE_FIREWALL_CHAT_OPENAI_MODEL | No | Specific OpenAI model for firewall chat (e.g., gpt-4o-mini). | |
| MAPLE_FIREWALL_CHAT_ANTHROPIC_MODEL | No | Specific Anthropic model for firewall chat (e.g., claude-sonnet-4-6). |
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/alnosarus/copymaple'
If you have feedback or need assistance with the MCP directory API, please join our Discord server