|
34 | 34 |
|
35 | 35 | `mcp-agent` gives you the following: |
36 | 36 |
|
37 | | -1. It fully implements MCP, and handles the pesky business of managing the lifecycle of MCP server connections so you don't have to. |
38 | | -2. It implements every pattern described in Anthropic's [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) in a _composable_ way, allowing you to chain these patterns together. |
| 37 | +1. **Full MCP support**: It _fully_ implements MCP, and handles the pesky business of managing the lifecycle of MCP server connections so you don't have to. |
| 38 | +2. **Effective agent patterns**: It implements every pattern described in Anthropic's [Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents) in a _composable_ way, allowing you to chain these patterns together. |
39 | 39 | 3. **Durable agents**: It works for simple agents and scales to sophisticated workflows built on [Temporal](https://temporal.io/) so you can pause, resume, and recover without any API changes to your agent. |
40 | 40 |
|
41 | | -**Altogether, this is the simplest and easiest way to build robust agent applications**. |
| 41 | +<u>Altogether, this is the simplest and easiest way to build robust agent applications</u>. |
42 | 42 |
|
43 | | -We welcome all kinds of [contributions](/CONTRIBUTING.md), feedback and your help in improving this. |
| 43 | +We welcome all kinds of [contributions](/CONTRIBUTING.md), feedback and your help in improving this project. |
| 44 | + |
| 45 | +**Minimal example** |
| 46 | + |
| 47 | +```python |
| 48 | +import asyncio |
| 49 | + |
| 50 | +from mcp_agent.app import MCPApp |
| 51 | +from mcp_agent.agents.agent import Agent |
| 52 | +from mcp_agent.workflows.llm.augmented_llm_openai import OpenAIAugmentedLLM |
| 53 | + |
| 54 | +app = MCPApp(name="hello_world") |
| 55 | + |
| 56 | +async def main(): |
| 57 | + async with app.run(): |
| 58 | + agent = Agent( |
| 59 | + name="finder", |
| 60 | + instruction="Use filesystem and fetch to answer questions.", |
| 61 | + server_names=["filesystem", "fetch"], |
| 62 | + ) |
| 63 | + async with agent: |
| 64 | + llm = await agent.attach_llm(OpenAIAugmentedLLM) |
| 65 | + answer = await llm.generate_str("Summarize README.md in two sentences.") |
| 66 | + print(answer) |
| 67 | + |
| 68 | + |
| 69 | +if __name__ == "__main__": |
| 70 | + asyncio.run(main()) |
| 71 | + |
| 72 | +# Add your LLM API key to `mcp_agent.secrets.yaml` or set it in env. |
| 73 | +# The [Getting Started guide](https://docs.mcp-agent.com/get-started/overview) walks through configuration and secrets in detail. |
| 74 | + |
| 75 | +``` |
44 | 76 |
|
45 | 77 | ## At a glance |
46 | 78 |
|
@@ -86,25 +118,52 @@ We welcome all kinds of [contributions](/CONTRIBUTING.md), feedback and your hel |
86 | 118 | <tr> |
87 | 119 | <td width="50%" valign="top"> |
88 | 120 | <h3>☁️ Deploy to Cloud</h3> |
89 | | - <p><b>Beta:</b> Deploy agents yourself, or use `mcp-c` for a managed agent runtime. Agents are exposed as MCP servers.</p> |
| 121 | + <p><b>Beta:</b> Deploy agents yourself, or use <b>mcp-c</b> for a managed agent runtime. All apps are deployed as MCP servers.</p> |
90 | 122 | <p> |
| 123 | + <a href="https://www.youtube.com/watch?v=0C4VY-3IVNU">Demo ↗</a> | |
91 | 124 | <a href="https://docs.mcp-agent.com/get-started/deploy-to-cloud">Cloud Quickstart ↗</a> | |
92 | 125 | <a href="https://docs.mcp-agent.com/cloud/overview">Docs ↗</a> |
93 | 126 | </p> |
94 | 127 | </td> |
95 | 128 | </tr> |
96 | 129 | </table> |
97 | 130 |
|
98 | | -## Documentation |
| 131 | +## Documentation & build with LLMs |
99 | 132 |
|
100 | 133 | mcp-agent's complete documentation is available at **[docs.mcp-agent.com](https://docs.mcp-agent.com)**, including full SDK guides, CLI reference, and advanced patterns. This readme gives a high-level overview to get you started. |
101 | 134 |
|
102 | | -### Build with LLMs |
103 | | - |
104 | 135 | - [`llms-full.txt`](https://docs.mcp-agent.com/llms-full.txt): contains entire documentation. |
105 | 136 | - [`llms.txt`](https://docs.mcp-agent.com/llms.txt): sitemap listing key pages in the docs. |
106 | 137 | - [docs MCP server](https://docs.mcp-agent.com/mcp) |
107 | 138 |
|
| 139 | +## Table of Contents |
| 140 | + |
| 141 | +- [Overview](#overview) |
| 142 | +- [Quickstart](#get-started) |
| 143 | +- [Why mcp-agent](#why-use-mcp-agent) |
| 144 | +- [Core concepts](#core-concepts) |
| 145 | + - [MCPApp](#mcpapp) |
| 146 | + - [Agents & AgentSpec](#agents--agentspec) |
| 147 | + - [Augmented LLM](#augmented-llm) |
| 148 | + - [Workflows & decorators](#workflows--decorators) |
| 149 | + - [Configuration & secrets](#configuration--secrets) |
| 150 | + - [MCP integration](#mcp-integration) |
| 151 | +- [Workflow patterns](#workflow-patterns) |
| 152 | +- [Durable execution](#durable-execution) |
| 153 | +- [Agent servers](#agent-servers) |
| 154 | +- [CLI reference](#cli-reference) |
| 155 | +- [Authentication](#authentication) |
| 156 | +- [Advanced](#advanced) |
| 157 | + - [Observability & controls](#observability--controls) |
| 158 | + - [Composing workflows](#composability) |
| 159 | + - [Signals & human input](#signaling-and-human-input) |
| 160 | + - [App configuration](#app-config) |
| 161 | + - [MCP server management](#mcp-server-management) |
| 162 | +- [Cloud deployment](#cloud-deployment) |
| 163 | +- [Examples](#examples) |
| 164 | +- [FAQ](#faq) |
| 165 | +- [Community & contributions](#community--contributions) |
| 166 | + |
108 | 167 | ## Get Started |
109 | 168 |
|
110 | 169 | > [!TIP] |
|
0 commit comments