Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEX_MODELSNoComma-separated list of Codex model identifiers (e.g., gpt-5-codex,gpt-5-codex-mini).
CODEX_ENABLEDNoSet to '1' to use the OpenAI Codex CLI provider (requires `codex` installed and logged in).
OLLAMA_MODELSNoComma-separated list of Ollama model names (e.g., qwen2.5-coder:14b,llama3.2).
ANTHROPIC_NAMESNoOptional comma-separated list of canonical names for the Anthropic models.
MOONSHOT_MODELSNoComma-separated list of Moonshot model IDs (e.g., kimi-k3,kimi-k2.6).
OLLAMA_BASE_URLNoBase URL for a local Ollama server (e.g., http://localhost:11434).
ANTHROPIC_MODELSNoComma-separated list of Anthropic model IDs (e.g., claude-opus-4-8,claude-sonnet-4-5).
MOONSHOT_API_KEYNoMoonshot (Kimi) API key.
ANTHROPIC_API_KEYNoAnthropic API key for access to Claude models.
OPENAI_COMPAT_KEYNoAPI key for the OpenAI-compatible endpoint.
CLAUDE_CODE_MODELSNoComma-separated list of Claude Code model identifiers (e.g., opus,sonnet).
OPENAI_COMPAT_NAMENoOptional canonical name for the model (e.g., google/gemini-flash).
CLAUDE_CODE_ENABLEDNoSet to '1' to use the Claude Code CLI provider (requires `claude` installed and logged in).
OPENAI_COMPAT_MODELNoModel ID for the OpenAI-compatible endpoint.
OPENAI_COMPAT_BASE_URLNoBase URL for an OpenAI-compatible endpoint (e.g., Google AI Studio, Groq, OpenRouter, DeepSeek).

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
volante_runA

Orchestrate GOAL across the configured models. Volante plans a task DAG, filters hard capability mismatches, and routes each sub-task to the best predicted fit using configured metadata and optional evaluation evidence. It runs tasks one-shot or in an agentic tool loop, then synthesizes one final answer. Returns that answer plus status, cost, and route evidence.

prefer sets the routing objective and defaults to "quality":

  • "quality" best predicted fit, price only breaks ties

  • "cheap" lowest cash cost that still meets the requirements

  • "local" prefer locally hosted models

  • "cash_protect_quota" spend cash before subscription quota

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.6/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no ambiguity or risk of selecting the wrong one. The tool's description clearly defines its singular purpose.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (volante_run). With only one tool, there is no inconsistency to evaluate.

Tool Count3/5

A single tool feels thin for a server, even if the tool is comprehensive. The orchestration role might benefit from separate tools for configuration or model management.

Completeness4/5

The tool covers the full orchestration workflow: planning, routing, execution, and synthesis. However, there is no tool for managing model metadata or configuration, which is a minor gap.

Maintenance

ActivityMaintained
ResponsivenessNo issues