Skip to main content
Glama
anteew
by anteew

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OAI_BASENoThe base URL for the OpenAI-compatible APIhttp://localhost:11434/v1
OAI_API_KEYNoOptional API key (some backends ignore it, Ollama allows any value)
OAI_TIMEOUT_MSNoOptional request timeout in milliseconds
OAI_DEFAULT_MODELNoFallback model name (e.g. llama3:latest)

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
openai_models_listB

List models from OpenAI-compatible backend (GET /v1/models).

openai_chat_completionsD

Create chat completion (POST /v1/chat/completions).

openai_embeddings_createC

Create embeddings (POST /v1/embeddings).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.6/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting different OpenAI API endpoints: chat completions, embeddings creation, and model listing. There is no overlap or ambiguity between these functions.

Naming Consistency4/5

The naming follows a consistent pattern with 'openai_' prefix and descriptive suffixes, though there's a minor deviation: 'openai_chat_completions' uses plural while 'openai_embeddings_create' uses singular verb form. Overall, the pattern is predictable and readable.

Tool Count3/5

With only 3 tools, the set feels thin for a server named 'RanchHand' which suggests broader functionality. While these cover core OpenAI operations, the limited scope may not fully represent what the server name implies.

Completeness3/5

For an OpenAI-compatible backend, the tools cover chat, embeddings, and models, but there are notable gaps in other common operations like image generation, audio processing, file operations, or fine-tuning endpoints. The surface is functional but incomplete for comprehensive OpenAI API coverage.