Vox MCP server
Multi-model AI gateway — 8 providers plus local models, no system prompt injection.
B83/100grade B
Adoption
Growing
1 stars121 downloads/wk
Reviews
Write oneNobody has reviewed Vox MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Vox MCP tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.3 · 2026-09-19 · same rubric, same numbers if you re-run it
no findings
- Code scan61 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 5 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
claude mcp add vox-mcp -- uvx vox-mcp
Vox MCP: common questions
- Is Vox MCP server safe?
- Mostly: it is graded B (83/100). Read the Vox MCP safety report
- How do I install Vox MCP?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Vox MCP need an API key?
- Yes. The registry entry asks for
GEMINI_API_KEY,OPENAI_API_KEY,ANTHROPIC_API_KEY,XAI_API_KEYand 3 more. - Is Vox MCP maintained?
- The last commit was 5 days ago (2026-09-14). The latest release is v0.6.0.
- What can I use instead of Vox MCP?
- Servers from other publishers that do the same job: prompt-protection MCP server, mcpm MCP server and Aletheia Runtime Safety & Scope Creep Filter MCP server. Compare all Vox MCP alternatives.
Alternatives to Vox MCP
Same job from other publishers: the closest match first, then the best rated.
- prompt-protectionScan prompts, tool definitions and model output for injection, and guard agent tool calls.not reviewedGrowingA
- mcpmMCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.not reviewedGrowingB
- Aletheia Runtime Safety & Scope Creep FilterDeterministic pre-execution filter that blocks known scope-creep and prompt-injection tool callsnot reviewedGrowingB
- NVIDIA ElementsNVIDIA Elements UI design system and agent tools for AI/ML, robotics, and autonomous vehicles.not reviewedEstablishedC
- Roast My Design SystemAudit your Design System and serve your Agent the rules that keep AI-written UI on-system.not reviewedEstablishedA