Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_WS_PORTNoPort for the WebSocket server3002
NAPKIN_MCP_PORTNoPort for the MCP HTTP server3003
NAPKIN_TRANSPORTNoTransport mode for the MCP server, either 'http' or 'stdio'http
ANTHROPIC_API_KEYNoAPI key for Anthropic, required for vision tools only
NAPKIN_EXPORT_DIRNoOptional base directory for relative exports of canvas files
NAPKIN_SESSION_TTL_MSNoTime-to-live in milliseconds for sessions7200000
NAPKIN_TRIGGER_WEBHOOKNoOptional global webhook URL for triggering agent responses to canvas updates
NAPKIN_COMPACT_TRIGGERSNoWhether to send compact trigger payloads (true/false)false
AGENT_TRIGGER_DEBOUNCE_MSNoDebounce time in milliseconds for triggering webhooks on canvas updates3000
NAPKIN_TRIGGER_INCLUDE_CANVASNoWhether to include full canvas data in trigger payloads (true/false)false

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/sshwarts/napkin'

If you have feedback or need assistance with the MCP directory API, please join our Discord server