{"type":"mcp_client","name":"mcp-agent","description":"Mcp-agent is a composable framework for building AI agents using the Model Context Protocol, inspired by Anthropic's research on effective agent design and standardized interfaces for AI assistants.","category":"AI","language":"Python","stars":8392,"forks":180,"owner":"lastmile-ai","github_url":"https://github.com/lastmile-ai/mcp-agent","homepage":null,"setup":"## Setup\n\nWe recommend using [uv](https://docs.astral.sh/uv/) to manage your Python projects:\n\n```bash\nuv add \"mcp-agent\"\n```\n\nAlternatively:\n\n```bash\npip install mcp-agent\n```\n\n### Quickstart\n\n> [!TIP]\n> The [`examples`](/examples) directory has several example applications to get started with.\n> To run an example, clone this repo, then:\n>\n> ```bash\n> cd examples/mcp_basic_agent # Or any other example\n> cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml # Update API keys\n> uv run main.py\n> ```","tools":"## Available Tools\n\n1.  **MCPApp**: Global state and app configuration.\n2.  **MCP server management**: `gen_client` and `MCPConnectionManager` to easily connect to MCP servers.\n3.  **Agent**: An entity that has access to a set of MCP servers and exposes them to an LLM as tool calls.\n4.  **AugmentedLLM**: An LLM that is enhanced with tools provided from a collection of MCP servers.\n5.  **Parallel**: Fan-out tasks to multiple sub-agents and fan-in the results.\n6.  **Router**: Given an input, route to the `top_k` most relevant categories.\n7.  **IntentClassifier**: Identifies the `top_k` Intents that most closely match a given input.\n8.  **Evaluator-Optimizer**: One LLM refines a response, another critiques it until a response exceeds a quality criteria.\n9.  **Orchestrator-workers**: A higher-level LLM generates a plan, then assigns them to sub-agents, and synthesizes the results.\n10. **Swarm**: A model-agnostic multi-agent pattern for task handling.","faq":null,"created_at":"2024-12-18T01:55:10+00:00","updated_at":"2025-03-28T23:46:35+00:00","source_url":"https://model-context-protocol.com/clients/build-ai-agents-model-context-protocol","related_articles":[]}