Anyscale

Anyscale MCP Connector for Claude

F

Orchestrate your Anyscale infrastructure — manage LLM queries, vectors, services, and cluster batch jobs directly from your AI agent.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Anyscale environment to your AI agent and manage both AI inference and backend scalable infrastructure natively through natural conversation.

What you can do

  • Model Discovery and Querying — List all active foundational models inside your environment and send conversational or zero-shot instruct prompts
  • Embeddings Pipeline — Generate semantic vector embeddings for arrays of text inputs directly in-flight
  • Services Fleet — Monitor deployed Ray services, fetch cluster states, and map live service endpoint configurations
  • Cluster Jobs — Query Ray batch jobs to inspect recent execution statuses and training metrics right from your terminal

How it works

  1. Subscribe to this server
  2. Provide your Anyscale API Key and Base URL
  3. Interface with your models, services, and Ray cluster via Claude, Cursor, or your favorite MCP agent

Scale up your AI operations without opening terminal panes to check Ray cluster status.

Who is this for?

  • AI & MLOps Engineers — automate the inspection of deployed models, jobs, and embeddings safely during CI workflows
  • Data Scientists — submit rapid completion tasks to specialized LLMs running inside your Anyscale VPC
  • Backend Developers — debug service health metrics and endpoint statuses without navigating the heavy cloud dashboard
distributed-computingllm-inferencevector-embeddingscluster-managementscalable-ai

7 tools expose this connector's capabilities to your AI agent.

list_models

g., meta-llama/Llama-2-70b-chat-hf). List available AI models on Anyscale Endpoints

chat_completion

Pass an array of messages with roles (user, assistant, system). Generate conversational responses via Anyscale LLMs

text_completion

Use for foundational instruct generation. Generate text completion using Anyscale generic completion API

generate_embeddings

Generate semantic vector embeddings for text

list_services

List Anyscale deployed services

get_service

Retrieve details about a specific Anyscale service

list_jobs

List Anyscale batch or training jobs

See how to talk to your AI agent using Anyscale.

List all active models from my Anyscale cluster.

I've fetched your models. Currently, you have `meta-llama/Llama-2-70b-chat-hf` and `mistralai/Mistral-7B-Instruct-v0.1` ready to receive inference traffic.

Check the status of our latest training jobs.

Looking up recent jobs. The 'daily_retrain_v3' job succeeded 5 hours ago. However, 'experimental_tuning_7b' was interrupted due to out-of-memory errors on node 12. Would you like me to fetch more service metadata on that specific node?

Generate vector embeddings for the text: 'The sun rises in the east and sets in the west'

I've passed the text to your configured Anyscale embedding model. The embedding array generated successfully with 768 dimensions. Since the array is large, I've mapped the output directly to the data pipeline.

Yes. First ask the agent to list the available model APIs using `list_models` so it can grab the precise namespace (e.g. meta-llama/Llama-3-70b-instruct). Then, ask it to run `chat_completion` pointing at that specific ID. You are now effectively chaining your local agent with an enterprise-sized foundational model in your own VPC.

Related Connectors