Volante runs on your own machine — the client starts it, so there is no endpoint to ping. 166 installs a week from pypi. Last commit 12 Aug 2026.
Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.
We read the source, 7 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
proc = subprocess.Popen(
found = detect_providers(dict(os.environ))
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add volante -- uvx volante
{
"mcpServers": {
"volante": {
"args": [
"volante"
],
"command": "uvx"
}
}
}
[mcp_servers.volante]
command = "uvx"
args = ["volante"]
{
"mcpServers": {
"volante": {
"args": [
"volante"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"volante": {
"args": [
"volante"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Anthropic API key.), ANTHROPIC_MODELS (Comma-separated Anthropic wire model ids.), ANTHROPIC_NAMES (Optional comma-separated canonical model ids.), ANTHROPIC_STRENGTHS (Shared comma-separated routing strengths.), ANTHROPIC_CONTEXT (Shared context-window tokens.), ANTHROPIC_MAX_OUTPUT (Shared maximum output tokens.), ANTHROPIC_TOOLS (Declare tool-call support (1 or 0).), ANTHROPIC_COST_IN (Shared USD per 1k input tokens.), ANTHROPIC_COST_OUT (Shared USD per 1k output tokens.), ANTHROPIC_TIER (Shared capability tier from 1 to 4.), MOONSHOT_API_KEY (Moonshot API key.), MOONSHOT_BASE_URL (Moonshot OpenAI-compatible base URL.), MOONSHOT_MODELS (Comma-separated Moonshot wire model ids.), MOONSHOT_NAMES (Optional comma-separated canonical model ids.), MOONSHOT_STRENGTHS (Shared comma-separated routing strengths.), MOONSHOT_CONTEXT (Shared context-window tokens.), MOONSHOT_MAX_OUTPUT (Shared maximum output tokens.), MOONSHOT_TOOLS (Declare tool-call support (1 or 0).), MOONSHOT_COST_IN (Shared USD per 1k input tokens.), MOONSHOT_COST_OUT (Shared USD per 1k output tokens.), MOONSHOT_TIER (Shared capability tier from 1 to 4.), OLLAMA_BASE_URL (Local Ollama OpenAI-compatible base URL.), OLLAMA_API_KEY (Optional credential for the Ollama endpoint.), OLLAMA_MODELS (Comma-separated Ollama wire model ids.), OLLAMA_NAMES (Optional comma-separated canonical model ids.), OLLAMA_STRENGTHS (Shared comma-separated routing strengths.), OLLAMA_CONTEXT (Shared context-window tokens.), OLLAMA_MAX_OUTPUT (Shared maximum output tokens.), OLLAMA_TOOLS (Declare tool-call support (1 or 0).), OLLAMA_COST_IN (Shared USD per 1k input tokens.), OLLAMA_COST_OUT (Shared USD per 1k output tokens.), OLLAMA_TIER (Shared capability tier from 1 to 4.), CLAUDE_CODE_ENABLED (Set to 1 to enable the logged-in Claude Code CLI.), CLAUDE_CODE_MODELS (Comma-separated Claude Code model ids.), CLAUDE_CODE_TIER (Shared capability tier from 1 to 4.), CLAUDE_CODE_MAX_OUTPUT (Shared maximum output tokens.), CLAUDE_CODE_TIMEOUT (Per-call timeout in seconds.), CLAUDE_CODE_SYSTEM_PROMPT_MODE (System-prompt mode: replace or append.), CODEX_ENABLED (Set to 1 to enable the logged-in Codex CLI.), CODEX_MODELS (Comma-separated Codex model ids.), CODEX_TIER (Required capability tier from 1 to 4 when enabled.), CODEX_CONTEXT (Shared context-window tokens.), CODEX_MAX_OUTPUT (Shared maximum output tokens.), CODEX_COST_IN (Shared API-equivalent input valuation.), CODEX_COST_OUT (Shared API-equivalent output valuation.), CODEX_TIMEOUT (Per-call timeout in seconds.), OPENAI_COMPAT_BASE_URL (Compatible slot 1 base URL.), OPENAI_COMPAT_KEY (Compatible slot 1 API key.), OPENAI_COMPAT_MODEL (Compatible slot 1 wire model id.), OPENAI_COMPAT_NAME (Compatible slot 1 canonical model id.), OPENAI_COMPAT_STRENGTHS (Compatible slot 1 comma-separated strengths.), OPENAI_COMPAT_CONTEXT (Compatible slot 1 context-window tokens.), OPENAI_COMPAT_MAX_OUTPUT (Compatible slot 1 maximum output tokens.), OPENAI_COMPAT_TOOLS (Compatible slot 1 tool-call support (1 or 0).), OPENAI_COMPAT_COST_IN (Compatible slot 1 input cost.), OPENAI_COMPAT_COST_OUT (Compatible slot 1 output cost.), OPENAI_COMPAT_TIER (Compatible slot 1 capability tier.), OPENAI_COMPAT_2_BASE_URL (Compatible slot 2 base URL.), OPENAI_COMPAT_2_KEY (Compatible slot 2 API key.), OPENAI_COMPAT_2_MODEL (Compatible slot 2 wire model id.), OPENAI_COMPAT_2_NAME (Compatible slot 2 canonical model id.), OPENAI_COMPAT_2_STRENGTHS (Compatible slot 2 comma-separated strengths.), OPENAI_COMPAT_2_CONTEXT (Compatible slot 2 context-window tokens.), OPENAI_COMPAT_2_MAX_OUTPUT (Compatible slot 2 maximum output tokens.), OPENAI_COMPAT_2_TOOLS (Compatible slot 2 tool-call support (1 or 0).), OPENAI_COMPAT_2_COST_IN (Compatible slot 2 input cost.), OPENAI_COMPAT_2_COST_OUT (Compatible slot 2 output cost.), OPENAI_COMPAT_2_TIER (Compatible slot 2 capability tier.), OPENAI_COMPAT_3_BASE_URL (Compatible slot 3 base URL.), OPENAI_COMPAT_3_KEY (Compatible slot 3 API key.), OPENAI_COMPAT_3_MODEL (Compatible slot 3 wire model id.), OPENAI_COMPAT_3_NAME (Compatible slot 3 canonical model id.), OPENAI_COMPAT_3_STRENGTHS (Compatible slot 3 comma-separated strengths.), OPENAI_COMPAT_3_CONTEXT (Compatible slot 3 context-window tokens.), OPENAI_COMPAT_3_MAX_OUTPUT (Compatible slot 3 maximum output tokens.), OPENAI_COMPAT_3_TOOLS (Compatible slot 3 tool-call support (1 or 0).), OPENAI_COMPAT_3_COST_IN (Compatible slot 3 input cost.), OPENAI_COMPAT_3_COST_OUT (Compatible slot 3 output cost.), OPENAI_COMPAT_3_TIER (Compatible slot 3 capability tier.), VOLANTE_QUALITY_PROFILES_FILE (Local strict-JSON quality-evidence file.), VOLANTE_MODEL_OVERRIDES_FILE (Local strict-JSON per-model metadata override file.), VOLANTE_FETCH_ALLOWLIST (Comma-separated domains that enable fetch_url.), VOLANTE_READ_ROOT (Root directory that enables confined read_file.), VOLANTE_SANDBOX (Agentic execution sandbox. Unset auto-selects docker when available and otherwise disables code execution; subprocess opts in to unisolated execution.), VOLANTE_MAX_SUBSCRIPTION_CALLS (Physical subscription calls allowed per run.).
The author declared them in the registry entry; get the values from the project itself.
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
Single entry point for the GOSCE portfolio: routes orchestrators to verified agents by capability, w
Read-only public CVE records, capability metadata, and agent instructions from Hacker Bob.
Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.
Read-only Objective-to-Capability Trust Router for source-traced MCP/API candidates.
Create evidence-backed video clips from owned recordings through PrismClip's OAuth-connected MCP.
Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Paid $0.001 x402 verify-before-pay Guard plus free capability procurement and provider routing.
Answers built from our own checks of this server.