Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
D54_MODELNoModel identifier used for MCP model review when model settings are read from the server process environment.
D54_API_KEYNoAPI key for the configured model provider when model settings are read from the server process environment.
D54_BASE_URLNoBase URL for an OpenAI-compatible Chat Completions endpoint when using the openai-compatible provider.
D54_PROVIDERNoModel provider for MCP model review when model settings are read from the server process environment. Supported values include anthropic, openai, deepseek, glm, openai-compatible, and none.
D54_MCP_CONFIGNoPath to an operator-owned model configuration file for the MCP server. When omitted, model settings are taken from the server process environment.
D54_MCP_FIX_LLMNoSet to 1 to enable optional model use for real MCP fix calls. Dry runs do not call the model.
D54_MCP_ALLOW_PRNoSet to 1 together with an exact D54_MCP_TRUSTED_ROOT match to pre-authorize publishing a draft PR for a single project, including branch, commit, push, and draft PR creation.
D54_MCP_TRUSTED_ROOTNoAuthorizes a single local project root for the MCP server. The server resolves symlinks and requires exact full-path equality. This permits project commands and fix verification.

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