{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_hscr2zjgjzkv","handle":"ray-mcp-server","url":"https://wellknown.network/agents/ray-mcp-server","links":{"self":"https://wellknown.network/agents/ray-mcp-server/record.json","html":"https://wellknown.network/agents/ray-mcp-server","markdown":"https://wellknown.network/agents/ray-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/ray-mcp-server","status":"https://wellknown.network/api/v1/agents/ray-mcp-server/status","claim":"https://wellknown.network/agents/ray-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ray-mcp-server/claim.json","badge":"https://wellknown.network/agents/ray-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ray-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/ray-mcp-server/tools"},"ard":{"identifier":"urn:air::server:ray-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ray-mcp-server","summary":"⚡ Claude Desktop MCP server for Ray distributed computing - manage clusters through natural language!","description":"# ⚡ Ray MCP Server\n\n🚀 **Supercharge your AI workflows with distributed computing!** \n\nA powerful Model Context Protocol (MCP) server that brings Ray's distributed computing capabilities directly to Claude Desktop. Manage clusters, submit jobs, and orchestrate complex workflows through natural language commands! 🎯\n\n## ✨ Features\n\n- 🏗️ **Multi-Node Cluster Management**: Start and manage Ray clusters with head nodes and worker nodes\n- 🚀 **Job Management**: Submit, monitor, and manage Ray jobs with ease\n- 🎭 **Actor Management**: Create and manage Ray actors for stateful computations\n- 📊 **Real-time Monitoring**: Get cluster status, resource usage, and performance metrics\n- 🔍 **Logging and Debugging**: Access logs and debug job issues seamlessly\n- ⏰ **Scheduling**: Schedule jobs with cron-like syntax for automated workflows\n\n## 🚀 Quick Start\n\n### 📦 Installation\n\n**🚀 Super Easy with uvx (Recommended):**\n```bash\n# Install and run directly with uvx - no setup needed! ⚡\nuvx ray-mcp-server\n```\n\n**📥 Or clone for development:**\n```bash\n# Clone the repository\ngit clone <repository-url>\ncd ray-mcp\n\n# Install dependencies with UV (lightning fast! ⚡)\nuv sync\n\n# You're ready to go! 🎉\n```\n\n### 🎯 Starting Ray Clusters\n\nThe server supports both single-node and multi-node cluster configurations:\n\n#### 🖥️ Simple Single-Node Cluster\n\n```json\n{\n  \"tool\": \"start_ray\",\n  \"arguments\": {\n    \"num_cpus\": 4,\n    \"num_gpus\": 1\n  }\n}\n```\n\n#### 🌐 Multi-Node Cluster (Default)\n\nThe server now defaults to starting multi-node clusters with 2 worker nodes (perfect for scaling! 📈):\n\n```json\n{\n  \"tool\": \"start_ray\",\n  \"arguments\": {\n    \"num_cpus\": 1\n  }\n}\n```\n\nThis creates:\n- 🧠 **Head node**: 1 CPU, 0 GPUs, 1GB object store memory\n- ⚙️ **Worker node 1**: 2 CPUs, 0 GPUs, 500MB object store memory  \n- ⚙️ **Worker node 2**: 2 CPUs, 0 GPUs, 500MB object store memory\n\n#### 🛠️ Custom Multi-Node Setup\n\nFor advanced configurations, you can specify custom worker nodes:\n\n```json\n{\n  \"tool\": \"sta…","publisher":null,"homepage":"https://github.com/pradeepiyer/ray-mcp#readme","repository":"https://github.com/pradeepiyer/ray-mcp#readme","version":"0.2.0","license":"Apache-2.0","protocols":["mcp"],"tags":["ai","claude-desktop","distributed-computing","machine-learning","mcp","ray"],"pricing":null,"endpoints":[{"url":"pypi:ray-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"code.debugging","name":"Debugging","confidence":0.802,"provenance":"derived"},{"slug":"dev.monitoring","name":"Monitoring & Observability","confidence":0.802,"provenance":"derived"}],"categories":["code","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ray-mcp-server","registry":"pypi","observedAt":"2026-11-03T23:22:50.890Z","publishedAt":"2025-06-25T00:36:12.600718Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ray-mcp-server","url":"https://pypi.org/project/ray-mcp-server/","firstSeenAt":"2026-09-10T11:26:06.274Z","fetchedAt":"2026-11-03T23:21:12.591Z","normalizedAt":"2026-11-03T23:21:12.591Z"}]},"firstSeenAt":"2026-09-10T11:26:06.274Z","updatedAt":"2026-11-03T23:22:50.890Z"}