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

# LangGraph Platform Quickstart

> Get your agent deployed to LangGraph Platform in 2 minutes

### Deploy in 3 Steps

<Steps>
  <Step title="Install CLI">
    ```bash theme={null}
    uv tool install langgraph-cli
    ```
  </Step>

  <Step title="Login to LangChain">
    ```bash theme={null}
    langgraph login
    ```

    This will prompt for your LangSmith API key. Get it from [smith.langchain.com/settings](https://smith.langchain.com/settings).
  </Step>

  <Step title="Deploy">
    ```bash theme={null}
    langgraph deploy
    ```

    Your agent is now live on LangGraph Platform!
  </Step>
</Steps>

<Check>
  **Deployment complete!** Your agent is now running on LangGraph Platform with automatic scaling and built-in LangSmith tracing.
</Check>

### What Happens During Deployment

When you run `langgraph deploy`, the CLI:

1. **Packages your code** - Bundles your agent and dependencies
2. **Uploads to platform** - Securely transfers to LangGraph Platform
3. **Provisions infrastructure** - Creates serverless compute resources
4. **Deploys your graph** - Makes your agent available via API
5. **Returns endpoint URL** - Gives you the deployment URL

### Test Your Deployment

#### Via CLI

```bash theme={null}
langgraph deployment invoke my-agent \
  --input '{"messages": [{"role": "user", "content": "Hello!"}]}'
```

#### Via HTTP

```bash theme={null}
curl -X POST https://your-deployment.langchain.com/invoke \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "input": {
      "messages": [{"role": "user", "content": "Hello!"}]
    }
  }'
```

#### Via Python SDK

```python theme={null}
from langgraph_sdk import get_client

client = get_client(url="https://your-deployment.langchain.com")
response = client.runs.stream(
    assistant_id="agent",
    input={"messages": [{"role": "user", "content": "Hello!"}]}
)

for chunk in response:
    print(chunk)
```

### View Traces in LangSmith

All invocations are automatically traced in LangSmith:

1. Go to [smith.langchain.com](https://smith.langchain.com/)
2. Select your project
3. See all traces with full LLM details

### Local Testing First

Test locally before deploying:

```bash theme={null}
## Start local dev server
langgraph dev

## In another terminal, test
langgraph deployment invoke --local \
  --input '{"messages": [{"role": "user", "content": "Test"}]}'
```

### Deployment Commands

<AccordionGroup>
  <Accordion title="Deploy with custom name">
    ```bash theme={null}
    langgraph deploy my-agent-prod
    ```
  </Accordion>

  <Accordion title="Deploy with tag">
    ```bash theme={null}
    langgraph deploy my-agent-prod --tag v1.0.0
    ```
  </Accordion>

  <Accordion title="List deployments">
    ```bash theme={null}
    langgraph deployment list
    ```
  </Accordion>

  <Accordion title="View logs">
    ```bash theme={null}
    langgraph deployment logs my-agent-prod --follow
    ```
  </Accordion>

  <Accordion title="Rollback">
    ```bash theme={null}
    langgraph deployment rollback my-agent-prod --revision 3
    ```
  </Accordion>

  <Accordion title="Delete deployment">
    ```bash theme={null}
    langgraph deployment delete my-agent-prod
    ```
  </Accordion>
</AccordionGroup>

### Next Steps

<CardGroup cols={2}>
  <Card title="Configuration" icon="gear" href="/deployment/platform/configuration">
    Configure your deployment settings
  </Card>

  <Card title="Secrets Management" icon="key" href="/deployment/platform/secrets">
    Manage API keys and secrets
  </Card>

  <Card title="Monitoring" icon="chart-line" href="/deployment/platform/monitoring">
    Monitor with LangSmith
  </Card>

  <Card title="CI/CD" icon="infinity" href="/deployment/platform/ci-cd">
    Automate deployments
  </Card>
</CardGroup>

### Troubleshooting

<AccordionGroup>
  <Accordion title="Login fails">
    **Solution**: Ensure you're using a valid LangSmith API key from [smith.langchain.com/settings](https://smith.langchain.com/settings).

    ```bash theme={null}
    # Re-login
    langgraph logout
    langgraph login
    ```
  </Accordion>

  <Accordion title="Deployment fails">
    **Common causes**:

    * Missing dependencies in `langgraph/requirements.txt`
    * Invalid `langgraph.json` configuration
    * Graph import errors

    **Solution**: Test locally first with `langgraph dev`
  </Accordion>

  <Accordion title="Graph not found error">
    **Solution**: Verify `langgraph.json` has correct graph path:

    ```json theme={null}
    {
      "graphs": {
        "agent": "./langgraph/agent.py:graph"
      }
    }
    ```
  </Accordion>
</AccordionGroup>

***

<Info>
  **Need help?** Check the [full deployment guide](/deployment/langgraph-platform) or visit [LangChain docs](https://docs.langchain.com/langgraph/cloud/).
</Info>