mcpbeat Sign in

Volante MCP Server

local only

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.

Installs per day peak 325 · avg 41 · -45% w/w
a month agotoday
166
Installs / week
pypi · volante
1
Stars
0 open issues
12 Aug 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 7 h ago · rules 3dff92dd89df

Capabilities

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.

File ships in the package but is absent from the source [пакет] src/volante/__main__.py:1, [пакет] src/volante/breaker.py:1, [пакет] src/volante/feedback.py:1
этот файл ставится пользователю, но в репозитории его нет
Runs an external command [пакет] eval/harness.py:440
        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.

This code can reach further than it looks

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.

Three servers free · no card

Connect this server

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.

run in your terminal
claude mcp add volante -- uvx volante
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "volante": {
      "args": [
        "volante"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.volante]
command = "uvx"
args = ["volante"]
.cursor/mcp.json
{
  "mcpServers": {
    "volante": {
      "args": [
        "volante"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "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.

Alternatives to Volante

same job, measured the same way
Modelglass
by modelglass

Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.

answering
Gosce Portfolio Router
by mikerawsonnz

Single entry point for the GOSCE portfolio: routes orchestrators to verified agents by capability, w

2 tools answering
Hacker Bob public records
by bobnetsec

Read-only public CVE records, capability metadata, and agent instructions from Hacker Bob.

22 tools answering
Chp
by capabilityhostprotocol

Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.

9 tools answering
AI Objective Index
by isometric-architect

Read-only Objective-to-Capability Trust Router for source-traced MCP/API candidates.

63 installs/wk local only
PrismClip Automatic Video Clipping
by prismclip

Create evidence-backed video clips from owned recordings through PrismClip's OAuth-connected MCP.

answering
Routescore
by routescore

Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.

41 installs/wk 11 tools answering
AgentResolver Guard — Verify x402 Before Paying
by waxsway

Paid $0.001 x402 verify-before-pay Guard plus free capability procurement and provider routing.

2 tools answering

Volante — questions

Answers built from our own checks of this server.

Why is there no uptime for Volante?
Volante runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package volante was installed 166 times last week.
How do I connect Volante?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls volante straight from pypi; nothing to host, nothing to sign up for.
How many people use Volante?
The pypi package volante was installed 166 times in the last week. Week over week that is -45%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Volante open source?
Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.