Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_MODELNoModel name to use for LLM calls (e.g. gpt-4o-mini); takes precedence over config.json llm.model.
DOUYIN_MCP_URLNoHTTPS MCP endpoint address of the service (e.g. https://your-host:19425/mcp). When set, the client connects over Streamable HTTP and supplies the token via the Authorization: Bearer header.
OPENAI_API_KEYNoAPI key for the LLM provider used by AI reply generation features (takes precedence over config.json llm.api_key).
DOUYIN_MCP_DESTNoDestination used instead of DOUYIN_MCP_URL when connecting over restricted SSH.
OPENAI_BASE_URLNoBase URL of the LLM API (e.g. https://api.openai.com/v1). Provider is auto-detected from the URL; takes precedence over config.json llm.base_url.
DOUYIN_MCP_SSH_KEYNoPath to the SSH key used for the restricted SSH connection (configured together with DOUYIN_MCP_DEST).
DOUYIN_MCP_TOKEN_FILENoPath to a local file (chmod 600) containing the access token used for the HTTPS MCP endpoint.

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