> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mcp-agent.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Complete implementation of industry-standard agent patterns - model-agnostic, composable, and production-ready.

mcp-agent provides implementations for every pattern in [Anthropic's Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents), as well as the [OpenAI's Swarm](https://github.com/openai/swarm) pattern. Each pattern is model-agnostic, and exposed as an AugmentedLLM, making everything very composable.

<CardGroup cols={2}>
  <Card title="Parallel Workflow" href="/workflows/parallel" icon="arrows-split-up-and-left">
    Execute multiple tasks simultaneously with intelligent result aggregation
    and conflict resolution.
  </Card>

  {" "}

  <Card title="Router Pattern" href="/workflows/router" icon="route">
    Intelligent task routing based on content analysis, user intent, and dynamic
    conditions.
  </Card>

  {" "}

  <Card title="Intent Classifier" href="/workflows/intent-classifier" icon="brain">
    Advanced intent recognition with confidence scoring and hierarchical
    classification.
  </Card>

  {" "}

  <Card title="Evaluator-Optimizer" href="/workflows/evaluator-optimizer" icon="arrows-rotate">
    Quality control with LLM-as-judge evaluation and iterative response
    refinement.
  </Card>

  {" "}

  <Card title="Orchestrator" href="/workflows/orchestrator" icon="users">
    Complex multi-step workflows with dependency management and state
    coordination.
  </Card>

  <Card title="Swarm Pattern" href="/workflows/swarm" icon="hexagon">
    OpenAI Swarm-compatible multi-agent handoffs with context preservation.
  </Card>
</CardGroup>

<Card>
  **Next Steps:** Explore individual workflow patterns to see detailed
  implementation examples and learn how to combine them for your specific use
  cases.
</Card>