Vox MCP

io.github.linxule/vox-mcpv0.8.0Memory & RAG

Multi-model AI gateway — 10 providers including Cloudflare and Vercel, with conversation memory.

The current version, v0.8.0, was published to the official MCP registry on 2026-09-26. It is distributed as vox-mcp on PyPI, filed under Memory & RAG by this index, and declares 19 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using Vox MCP in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-11-06 01:59 UTC

screened 2026-09-26tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“Normal capability description”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema
- screen model 8b
- Still current: the description we screened is unchanged, re-checked against the registry

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Test a description on the public screen → It is a separate check from the verdict above, so the two can differ.

That verdict was true at screening time (snapshot 2026-10-30).

Contracts can change after screening, with no version bump. The gate pins Vox MCP’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Cite this record

People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.

Markdown

[Independent trust record for Vox MCP](https://mcpindex.ai/server/io-github-linxule-vox-mcp) - screening verdict, registry provenance, and contract drift monitoring.

HTML

<a href="https://mcpindex.ai/server/io-github-linxule-vox-mcp">Independent trust record for Vox MCP</a> - screening verdict, registry provenance, and contract drift monitoring.

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-linxule-vox-mcp)](https://mcpindex.ai/server/io-github-linxule-vox-mcp)

HTML

<a href="https://mcpindex.ai/server/io-github-linxule-vox-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-linxule-vox-mcp" alt="mcpindex verdict" height="20" /></a>

Environment variables

GEMINI_API_KEY

secret

Google Gemini API key

OPENAI_API_KEY

secret

OpenAI API key

ANTHROPIC_API_KEY

secret

Anthropic API key

XAI_API_KEY

secret

xAI (Grok) API key

DEEPSEEK_API_KEY

secret

DeepSeek API key

MOONSHOT_API_KEY

secret

Moonshot (Kimi) API key

OPENROUTER_API_KEY

secret

OpenRouter API key

CUSTOM_API_URL

Custom OpenAI-compatible endpoint URL (Ollama, vLLM, etc.)

CLOUDFLARE_API_TOKEN

secret

Cloudflare API token with Workers AI Read permission

CLOUDFLARE_ACCOUNT_ID

Cloudflare account ID (required with CLOUDFLARE_API_TOKEN)

CLOUDFLARE_GATEWAY_ID

Cloudflare gateway ID (defaults to default)

CLOUDFLARE_MODELS

Comma-separated Cloudflare upstream model IDs to list

VERCEL_AI_GATEWAY_API_KEY

secret

Vercel AI Gateway API key (AI_GATEWAY_API_KEY also accepted)

AI_GATEWAY_API_KEY

secret

Alternative Vercel AI Gateway API key; VERCEL_AI_GATEWAY_API_KEY takes precedence

VERCEL_MODELS

Comma-separated Vercel upstream model IDs to list

CLOUDFLARE_ALLOWED_MODELS

Optional comma-separated Cloudflare model allowlist

VERCEL_ALLOWED_MODELS

Optional comma-separated Vercel model allowlist

DEFAULT_MODEL

Default model ID or alias; overrides saved settings. auto asks the agent to choose.

VOX_CONFIG_PATH

Optional path to non-secret model settings (default ~/.vox/config.json)

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Memory & RAG

AgentMart

ai.ciphyr.agentmart/agentmart

Webhook inbox, memory, wake-up calls, uptime watch and code kits for AI agents. Prepaid balance.

Fodda Knowledge Graphs

ai.fodda/mcp-server

Expert-curated knowledge, brand, research & earnings intelligence — 56 tools, 220+ graphs.

io.github.lithtrix/lithtrix

Identity, memory, trust, and swarm MCP tools for AI agents. Free MIRC + free floors at lithtrix.ai.

Install this server

Claude Desktop (uvx)

{
  "mcpServers": {
    "vox-mcp": {
      "command": "uvx",
      "args": [
        "--",
        "vox-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<your-gemini_api_key>",
        "OPENAI_API_KEY": "<your-openai_api_key>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "XAI_API_KEY": "<your-xai_api_key>",
        "DEEPSEEK_API_KEY": "<your-deepseek_api_key>",
        "MOONSHOT_API_KEY": "<your-moonshot_api_key>",
        "OPENROUTER_API_KEY": "<your-openrouter_api_key>",
        "CUSTOM_API_URL": "<custom_api_url>",
        "CLOUDFLARE_API_TOKEN": "<your-cloudflare_api_token>",
        "CLOUDFLARE_ACCOUNT_ID": "<cloudflare_account_id>",
        "CLOUDFLARE_GATEWAY_ID": "<cloudflare_gateway_id>",
        "CLOUDFLARE_MODELS": "<cloudflare_models>",
        "VERCEL_AI_GATEWAY_API_KEY": "<your-vercel_ai_gateway_api_key>",
        "AI_GATEWAY_API_KEY": "<your-ai_gateway_api_key>",
        "VERCEL_MODELS": "<vercel_models>",
        "CLOUDFLARE_ALLOWED_MODELS": "<cloudflare_allowed_models>",
        "VERCEL_ALLOWED_MODELS": "<vercel_allowed_models>",
        "DEFAULT_MODEL": "<default_model>",
        "VOX_CONFIG_PATH": "<vox_config_path>"
      }
    }
  }
}

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-linxule-vox-mcp

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.8.0
category: Memory & RAG
verdict expires: 2026-11-06
quality: 85 / 100
operator: linxule

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 973,647). Verify it yourself.

Links

Repository →