---
title: "Compose router, evaluator, and handoff workflows over MCP servers with mcp-agent"
description: "Connect LLMs to MCP servers through composable patterns like router, evaluator-optimizer, and orchestrator flows without hand-managing server lifecycles."
verification: "security_reviewed"
source: "https://github.com/lastmile-ai/mcp-agent"
author: "LastMile AI"
publisher_type: "open_source_project"
category:
  - "Templates & Workflows"
framework:
  - "MCP"
tool_ecosystem:
  github_repo: "lastmile-ai/mcp-agent"
  github_stars: 8276
  npm_package: "mcp-agent"
  npm_weekly_downloads: 29247
---

# Compose router, evaluator, and handoff workflows over MCP servers with mcp-agent

Connect LLMs to MCP servers through composable patterns like router, evaluator-optimizer, and orchestrator flows without hand-managing server lifecycles.

## Prerequisites

Python runtime, MCP servers, LLM API key, optional Temporal for durable workflows

## Installation

Choose whichever fits your setup:

1. Copy this skill folder into your local skills directory.
2. Clone the repo and symlink or copy the skill into your agent workspace.
3. Add the repo as a git submodule if you manage shared skills centrally.
4. Install it through your internal provisioning or packaging workflow.
5. Download the folder directly from GitHub and place it in your skills collection.

Install command or upstream instructions:

```
Install mcp-agent from the upstream package, configure your MCP servers and model credentials, then compose the desired workflow pattern from the quickstart examples.
```

## Documentation

- https://docs.mcp-agent.com/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/compose-router-evaluator-and-handoff-workflows-over-mcp-servers-with-mcp-agent/)