4,500+ servers built on MCP Fusion
Vinkius
Anyscale logo
Vinkius
Claude Code logo

How to Use the Anyscale MCP in Claude Code

Query Anyscale models and monitor cluster jobs directly from your terminal with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Anyscale MCP on Cursor AI Code Editor MCP Client Anyscale MCP on Claude Desktop App MCP Integration Anyscale MCP on OpenAI Agents SDK MCP Compatible Anyscale MCP on Visual Studio Code MCP Extension Client Anyscale MCP on GitHub Copilot AI Agent MCP Integration Anyscale MCP on Google Gemini AI MCP Integration Anyscale MCP on Lovable AI Development MCP Client Anyscale MCP on Mistral AI Agents MCP Compatible Anyscale MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Anyscale MCP to Claude Code

Create your Vinkius account to connect Anyscale to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Terminal-based model querying with this MCP Server

The `chat_completion` tool sends structured chat messages to your Anyscale endpoints directly from your CLI. Claude Code runs this tool to test model behavior or generate script logic without opening a browser. When you need simpler instruct outputs, the `text_completion` tool handles raw text generation tasks. This allows your terminal agent to parse and format quick outputs inside your shell scripts.

Monitor Anyscale services directly in your shell

The `list_services` tool lists all active deployments on your cluster to verify system health. Claude Code runs this check using the MCP toolset inside your CI/CD pipelines to ensure endpoints are live before running integration tests. For detailed debugging, the `get_service` tool fetches configuration details for a specific deployment. This lets your terminal agent diagnose routing issues or resource constraints directly from your SSH session.

Manage batch training jobs via Claude Code

The `list_jobs` tool tracks active training runs and batch processing pipelines on your infrastructure. Claude Code queries this list to monitor long-running cluster operations during deployment cycles. Combined with the `list_models` tool, your agent checks when a new fine-tuned model becomes available. This lets you automate model promotion steps directly within your terminal workspace.

Setup guide

Set up Anyscale MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see anyscale-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Anyscale transactions." It will automatically discover and invoke the available Anyscale tools.

Terminal
claude mcp add --transport http anyscale-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Anyscale MCP in Claude Code

Run `claude mcp add --transport http anyscale-mcp -- ` in your terminal. This saves the configuration directly to your local `~/.claude.json` file.
Yes. Claude Code uses the `list_jobs` tool to check the status of active cluster runs and outputs the results straight to your terminal.
Yes. Claude Code calls the `generate_embeddings` tool to convert text inputs into vector representations, making it easy to test indexing scripts from the command line.
It uses the HTTP transport protocol. You configure this by passing the transport flag during the initial setup command in your terminal.
Yes. Your cluster job configurations, prompt messages, and vector embeddings are routed through secure, ephemeral V8 isolates. No data is stored or logged on Vinkius servers, maintaining strict isolation for your proprietary model pipelines.

Start using the Anyscale MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 7 tools

We've already built the connector for Anyscale. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 7 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.