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

# Server: Agents MCP

> Deploy agents as MCP servers using Agent.launch(protocol='mcp')

Deploy single or multi-agent systems as MCP (Model Context Protocol) servers for Claude Desktop, Cursor, and other MCP clients.

## Quick Start

<Steps>
  <Step title="Install Dependencies">
    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    pip install "praisonaiagents[mcp]"
    ```
  </Step>

  <Step title="Set API Key">
    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    export OPENAI_API_KEY="your-key"
    ```
  </Step>

  <Step title="Create Agent MCP Server">
    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent

    agent = Agent(
        name="TweetAgent",
        instructions="Create engaging tweets",
        llm="gpt-4o-mini"
    )
    agent.launch(port=8080, protocol="mcp")
    ```
  </Step>

  <Step title="Verify">
    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    curl http://localhost:8080/sse
    ```
  </Step>
</Steps>

## Single Agent as MCP

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent

agent = Agent(
    name="TweetAgent",
    instructions="Create engaging tweets",
    llm="gpt-4o-mini"
)
agent.launch(port=8080, protocol="mcp")
```

**Expected Output:**

```
🚀 Agent 'TweetAgent' MCP server starting on http://0.0.0.0:8080
📡 MCP SSE endpoint available at /sse
📢 MCP messages post to /messages/
🛠️ Available MCP tools: execute_tweetagent_task
```

## Multi-Agent as MCP

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, AgentTeam

researcher = Agent(name="Researcher", instructions="Research topics", llm="gpt-4o-mini")
writer = Agent(name="Writer", instructions="Write content", llm="gpt-4o-mini")

agents = AgentTeam(agents=[researcher, writer])
agents.launch(port=8080, protocol="mcp")
```

**Expected Output:**

```
🚀 Agents MCP Workflow server starting on http://0.0.0.0:8080
📡 MCP SSE endpoint available at /sse
📢 MCP messages post to /messages/
🛠️ Available MCP tools: execute_workflow
🔄 Agents in MCP workflow: Researcher, Writer
```

## MCP Endpoints

| Endpoint     | Method | Description            |
| ------------ | ------ | ---------------------- |
| `/sse`       | GET    | SSE connection for MCP |
| `/messages/` | POST   | Send MCP messages      |

## launch() Parameters

| Parameter  | Type | Default   | Description   |
| ---------- | ---- | --------- | ------------- |
| `port`     | int  | `8000`    | Server port   |
| `host`     | str  | `0.0.0.0` | Server host   |
| `protocol` | str  | `mcp`     | Must be `mcp` |
| `debug`    | bool | `False`   | Debug mode    |

## Connect MCP Client

**Claude Desktop** (`claude_desktop_config.json`):

```json theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
{
  "mcpServers": {
    "praisonai-agent": {
      "url": "http://localhost:8080/sse"
    }
  }
}
```

**Cursor** (`.cursor/mcp.json`):

```json theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
{
  "mcpServers": {
    "praisonai-agent": {
      "url": "http://localhost:8080/sse"
    }
  }
}
```

## Test MCP Tools

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# List tools
curl -X POST http://localhost:8080/messages/ \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}'

# Call tool
curl -X POST http://localhost:8080/messages/ \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {"name": "execute_tweetagent_task", "arguments": {"task": "Create a tweet about AI"}},
    "id": 2
  }'
```

## Docker Deployment

**app.py:**

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent

agent = Agent(instructions="Create tweets", llm="gpt-4o-mini")
agent.launch(port=8080, protocol="mcp")
```

**Dockerfile:**

```dockerfile theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 8080
CMD ["python", "app.py"]
```

**requirements.txt:**

```
praisonaiagents[mcp]
```

**Build and run:**

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
docker build -t agent-mcp-server .
docker run -p 8080:8080 -e OPENAI_API_KEY=$OPENAI_API_KEY agent-mcp-server
```

## Troubleshooting

| Issue              | Fix                                  |
| ------------------ | ------------------------------------ |
| Port in use        | `lsof -i :8080`                      |
| Missing deps       | `pip install "praisonaiagents[mcp]"` |
| No API key         | `export OPENAI_API_KEY="your-key"`   |
| SSE not connecting | Check firewall, use `host="0.0.0.0"` |

## Related

* [Tools MCP](./tools-mcp) - Deploy tools as MCP server
* [Recipes MCP](./recipes-mcp) - Deploy recipes as MCP server
* [PraisonAI MCP](./praisonai-mcp) - Full PraisonAI MCP server
* [Agents HTTP](./agents) - Deploy as HTTP server