Skip to main content
Glama
van-reflect

reflect-memory

by van-reflect

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RM_PORTNoHTTP port (default: 3000)
RM_API_KEYYesUser key -- full access to all endpoints (required)
RM_DB_PATHNoSQLite file path (default: /data/reflect-memory.db)
RM_MODEL_NAMEYesModel identifier, e.g. gpt-4o-mini (required)
RM_CHAT_XAI_KEYNoGrok API key for chat
RM_MODEL_API_KEYYesOpenAI (or compatible) API key (required)
RM_SYSTEM_PROMPTNoSystem prompt for AI queries
RM_MODEL_BASE_URLNoModel API base URL (default: https://api.openai.com/v1)
RM_CHAT_GOOGLE_KEYNoGemini API key for chat
RM_CHAT_OPENAI_KEYNoChat OpenAI key (defaults to RM_MODEL_API_KEY)
RM_AGENT_KEY_CLAUDENoAgent key for Claude (enables MCP endpoint)
RM_MODEL_MAX_TOKENSNoMax tokens (default: 1024)
RM_AGENT_KEY_CHATGPTNoAgent key for ChatGPT (enables MCP endpoint)
RM_MODEL_TEMPERATURENoTemperature (default: 0.7)
RM_CHAT_ANTHROPIC_KEYNoClaude API key for chat
RM_CHAT_PERPLEXITY_KEYNoPerplexity API key for chat
RM_DASHBOARD_JWT_SECRETNoDashboard JWT secret (minimum 32 characters)
RM_DASHBOARD_SERVICE_KEYNoDashboard service key (required for dashboard)

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/van-reflect/Reflect-Memory'

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