{"type":"mcp_server","name":"mastra","description":"Mastra is a TypeScript framework for rapidly building AI applications, offering primitives like workflows, agents, RAG, integrations, and evals, supporting local or serverless cloud deployment with unified LLM provider interaction.","category":"AI","language":"TypeScript","stars":25648,"forks":544,"owner":"mastra-ai","github_url":"https://github.com/mastra-ai/mastra","homepage":"https://mastra.ai","setup":"## Setup\n\n### Prerequisites\n\n- Node.js (v20.0+)\n\n## Get an LLM provider API key\n\nIf you don't have an API key for an LLM provider, you can get one from OpenAI, Anthropic, Google Gemini, Groq, or Cerebras.\n\n## Create a new project\n\nUse `create-mastra` to start building a new Mastra application:\n\n```bash\nnpx create-mastra@latest\n```\n\n### Run the script\n\nRun `mastra dev` to open the Mastra playground:\n\n```bash copy\nnpm run dev\n```\n\nIf you're using Anthropic, set the `ANTHROPIC_API_KEY`. If you're using Gemini, set the `GOOGLE_GENERATIVE_AI_API_KEY`.","tools":"## Available Tools\n\n1.  LLM Models (Uses the Vercel AI SDK for model routing, providing a unified interface to interact with any LLM provider.)\n2.  Agents (Provide LLM models with tools, workflows, and synced data.)\n3.  Tools (Typed functions that can be executed by agents or workflows, with built-in integration access and parameter validation.)\n4.  Workflows (Durable graph-based state machines with loops, branching, and error handling.)\n5.  RAG (Retrieval-augmented generation lets you construct a knowledge base for agents.)\n6.  Integrations (Auto-generated, type-safe API clients for third-party services.)\n7.  Evals (Automated tests that evaluate LLM outputs using model-graded, rule-based, and statistical methods.)","faq":null,"created_at":"2024-08-06T20:44:31+00:00","updated_at":"2025-03-28T23:56:04+00:00","source_url":"https://model-context-protocol.com/servers/typescript-ai-agent-framework-build-llm","related_articles":[]}