Skip to main content
Glama
fernandogarzaaa

Steward MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
STEWARD_DBNoSQLite file used for storage (events, reminders, notes, prefs).~/.steward/steward.db
STEWARD_MCP_URLNoWhere the agent finds the MCP server.http://127.0.0.1:8899/mcp
STEWARD_MCP_HOSTNoMCP server bind host (Streamable HTTP).127.0.0.1
STEWARD_MCP_PORTNoMCP server bind port (Streamable HTTP).8899
STEWARD_MODEL_IDNoModel id for the OpenAI-compatible endpoint.
STEWARD_WEB_HOSTNoWeb app bind host.127.0.0.1
STEWARD_WEB_PORTNoWeb app bind port.8898
STEWARD_AWS_REGIONNoBedrock region (e.g. us-east-1).AWS config chain
STEWARD_MODEL_API_KEYNoKey for the OpenAI-compatible endpoint (or "not-needed").
STEWARD_MODEL_BASE_URLNoBase URL of an OpenAI-compatible endpoint (e.g. http://127.0.0.1:11434/v1).
STEWARD_MODEL_PROVIDERNoWhich model provider to use: bedrock, openai-compatible, or auto. With AWS credentials present and no STEWARD_MODEL_BASE_URL, Bedrock is selected automatically. With nothing configured, the agent raises a clear error instead of guessing.auto
STEWARD_BEDROCK_MODEL_IDNoBedrock model id (e.g. amazon.nova-micro-v1:0, or any Bedrock id).amazon.nova-micro-v1:0

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

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