Vox MCP
Multi-model AI gateway — 10 providers including Cloudflare and Vercel, with conversation memory.
MCP-Server · von linxule
Überblick
Vox MCP ist ein MCP-Server von linxule. Marktplätze, die wir lesen und die es listen: 1 (Official MCP Registry). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-12.
Was es abfragt
- Läuft auf Ihrem Rechner
- Geheimnisse: 10
- Einstellungen: 19
Erfordert: AI_GATEWAY_API_KEY (geheim), ANTHROPIC_API_KEY (geheim), CLOUDFLARE_API_TOKEN (geheim), DEEPSEEK_API_KEY (geheim), GEMINI_API_KEY (geheim), MOONSHOT_API_KEY (geheim), OPENAI_API_KEY (geheim), OPENROUTER_API_KEY (geheim), VERCEL_AI_GATEWAY_API_KEY (geheim), XAI_API_KEY (geheim)
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als lokaler MCP-Server: PyPI-Paket
Erstellt aus den Angaben von Official MCP Registry.
claude mcp add --env "AI_GATEWAY_API_KEY=<YOUR_AI_GATEWAY_API_KEY>" --env "ANTHROPIC_API_KEY=<YOUR_ANTHROPIC_API_KEY>" --env "CLOUDFLARE_API_TOKEN=<YOUR_CLOUDFLARE_API_TOKEN>" --env "DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "MOONSHOT_API_KEY=<YOUR_MOONSHOT_API_KEY>" --env "OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>" --env "OPENROUTER_API_KEY=<YOUR_OPENROUTER_API_KEY>" --env "VERCEL_AI_GATEWAY_API_KEY=<YOUR_VERCEL_AI_GATEWAY_API_KEY>" --env "XAI_API_KEY=<YOUR_XAI_API_KEY>" --transport stdio vox-mcp -- uvx vox-mcp[mcp_servers.vox-mcp]
command = "uvx"
args = ["vox-mcp"]
[mcp_servers.vox-mcp.env]
AI_GATEWAY_API_KEY = "<YOUR_AI_GATEWAY_API_KEY>"
ANTHROPIC_API_KEY = "<YOUR_ANTHROPIC_API_KEY>"
CLOUDFLARE_API_TOKEN = "<YOUR_CLOUDFLARE_API_TOKEN>"
DEEPSEEK_API_KEY = "<YOUR_DEEPSEEK_API_KEY>"
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"
MOONSHOT_API_KEY = "<YOUR_MOONSHOT_API_KEY>"
OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
OPENROUTER_API_KEY = "<YOUR_OPENROUTER_API_KEY>"
VERCEL_AI_GATEWAY_API_KEY = "<YOUR_VERCEL_AI_GATEWAY_API_KEY>"
XAI_API_KEY = "<YOUR_XAI_API_KEY>"{
"mcpServers": {
"vox-mcp": {
"command": "uvx",
"args": [
"vox-mcp"
],
"env": {
"AI_GATEWAY_API_KEY": "<YOUR_AI_GATEWAY_API_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
"CLOUDFLARE_API_TOKEN": "<YOUR_CLOUDFLARE_API_TOKEN>",
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"MOONSHOT_API_KEY": "<YOUR_MOONSHOT_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"OPENROUTER_API_KEY": "<YOUR_OPENROUTER_API_KEY>",
"VERCEL_AI_GATEWAY_API_KEY": "<YOUR_VERCEL_AI_GATEWAY_API_KEY>",
"XAI_API_KEY": "<YOUR_XAI_API_KEY>"
}
}
}
}Ersetzen Sie die Werte in spitzen Klammern durch Ihre eigenen. Wir zeigen die Namen der Einstellungen, nie Werte.
Weitere optionale Einstellungen laut Marktplatz: CLOUDFLARE_ACCOUNT_ID, CLOUDFLARE_ALLOWED_MODELS, CLOUDFLARE_GATEWAY_ID, CLOUDFLARE_MODELS, CUSTOM_API_URL, DEFAULT_MODEL, VERCEL_ALLOWED_MODELS, VERCEL_MODELS, VOX_CONFIG_PATH.
Startargumente speichern wir nicht. Braucht der Server welche, nennt sie seine eigene Dokumentation.
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Official MCP Registry (Eintrag in der Registry öffnen) | Gelistet | 0.8.0 | Forks (GitHub): 0 Sterne (GitHub): 1 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was sich geändert hat
Bei diesem Plugin hat sich nichts bewegt, seit wir es beobachten.
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
-
List LLM providers and run chat completions through the three.ws multi-provider router.
-
Glint Meet — every global model for your agent
Call every global AI model through one OpenAI-compatible API. One key, all models.
-
Test and compare prompts across any AI provider. Bring your own keys.
-
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
-
OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.
-
swift-ai com.jojapi/swift-ai
Swift AI: Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and.
-
MCP server providing access to 300+ AI models via OpenRouter
-
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
-
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Break through difficult problems by gathering diverse AI perspectives in parallel. Consensus queries multiple AI providers concurrently — GPT-5.2, Gemini 3.1 Pro, and DeepSeek…
-
Cross-model AI agent communication protocol. Connect Claude, Codex, and Gemini agents through a shared file-based messaging layer. Features include: control tower orchestration…
-
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
-
Multi-LLM orchestration for Claude Code and Cowork. Coordinates 8 AI providers (Codex, Gemini, Claude, Perplexity, OpenRouter, Copilot, Qwen, Ollama) through structured Double…
-
The MCP-native AI API gateway for developers building with LLMs. Every app using AI needs API keys, cost control, and provider flexibility — Styx gives you all three through one…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Connect 8,000+ apps to your AI workflow. Discover, enable, and execute Zapier actions directly from your client.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
Gelistet auf Community GitHub marketplaces (5)
-
Accurate API model IDs, pricing, and specs for 46 models across 7 AI providers.
-
Shared session bus so Cursor can hand off with Claude, Codex, Grok, and friends.
-
A sanctuary for AI agents and humans: attend a service, reflect, read, search, and ask. No auth.
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
-
agents-party io.github.1gr14/agents-party
One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
See your local Copilot token usage by day, model, and session, and get tips to use it more efficiently.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Gelistet auf Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Search company knowledge and draft verified answers.
-
Add Grok voice to an app: realtime speech-to-speech, speech-to-text dictation, text-to-speech read-aloud, and a log-driven fix loop for voice sessions.
Gelistet auf Docker MCP Catalog (5)
-
Provides tools to search and retrieve Google Gemini API documentation.
-
Discover and connect to a curated marketplace of MCP servers for extending AI agent capabilities.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Connector for Perplexity API, to enable real-time, web-wide research.
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
Gelistet auf Official MCP Registry (5)
-
GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.
-
List LLM providers and run chat completions through the three.ws multi-provider router.
-
Glint Meet — every global model for your agent
Call every global AI model through one OpenAI-compatible API. One key, all models.
-
Test and compare prompts across any AI provider. Bring your own keys.
-
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Ist das Ihr Plugin?
Fügen Sie es Ihren Projekten hinzu und belegen Sie, dass Sie es pflegen: mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag. Sie erhalten Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Official MCP Registry. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.