Volante
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_MODELS | No | Comma-separated list of Codex model identifiers (e.g., gpt-5-codex,gpt-5-codex-mini). | |
| CODEX_ENABLED | No | Set to '1' to use the OpenAI Codex CLI provider (requires `codex` installed and logged in). | |
| OLLAMA_MODELS | No | Comma-separated list of Ollama model names (e.g., qwen2.5-coder:14b,llama3.2). | |
| ANTHROPIC_NAMES | No | Optional comma-separated list of canonical names for the Anthropic models. | |
| MOONSHOT_MODELS | No | Comma-separated list of Moonshot model IDs (e.g., kimi-k3,kimi-k2.6). | |
| OLLAMA_BASE_URL | No | Base URL for a local Ollama server (e.g., http://localhost:11434). | |
| ANTHROPIC_MODELS | No | Comma-separated list of Anthropic model IDs (e.g., claude-opus-4-8,claude-sonnet-4-5). | |
| MOONSHOT_API_KEY | No | Moonshot (Kimi) API key. | |
| ANTHROPIC_API_KEY | No | Anthropic API key for access to Claude models. | |
| OPENAI_COMPAT_KEY | No | API key for the OpenAI-compatible endpoint. | |
| CLAUDE_CODE_MODELS | No | Comma-separated list of Claude Code model identifiers (e.g., opus,sonnet). | |
| OPENAI_COMPAT_NAME | No | Optional canonical name for the model (e.g., google/gemini-flash). | |
| CLAUDE_CODE_ENABLED | No | Set to '1' to use the Claude Code CLI provider (requires `claude` installed and logged in). | |
| OPENAI_COMPAT_MODEL | No | Model ID for the OpenAI-compatible endpoint. | |
| OPENAI_COMPAT_BASE_URL | No | Base 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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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.
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
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.
The single tool name follows a clear verb_noun pattern (volante_run). With only one tool, there is no inconsistency to evaluate.
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.
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.