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

# Langdock

> Connect Qontext to Langdock

Connect Qontext to Langdock via MCP to power conversations and automations with up-to-date company context.

With Qontext + Langdock, you can:

* Connect Qontext directly inside Langdock (chat, agent, or workflow)
* Automatically pull relevant, up-to-date context for every prompt
* Keep full governance and permissions in Qontext
* Use Qontext in **Chat**, **Agent**, and **Workflow** modes

***

## Installation

<Steps>
  <Step title="Open Langdock Integrations">
    In your Langdock workspace, go to **Integrations** and click on **Add integration**. Then, choose **Start from scratch** to add a new MCP-based connection.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_add_integration.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=fdee35284874007c8649867b89272cf3" alt="Langdock add integration" className="rounded-lg" style={{ maxWidth: '100%' }} width="2994" height="1135" data-path="ai-tools/images/langdock/langdock_add_integration.png" />
  </Step>

  <Step title="Connect Qontext MCP">
    Choose **Connect remote MCP**. Add the Qontext MCP server URL and choose **OAuth 2.0** as authentication method:

    **MCP server URL:**

    ```text theme={null}
    https://api.qontext.ai/mcp
    ```

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_start_mcp.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=c09b81885f0c6dc1f4c4b1e649238adf" alt="Langdock start MCP" className="rounded-lg" style={{ maxWidth: '70%' }} width="1368" height="1120" data-path="ai-tools/images/langdock/langdock_start_mcp.png" />
  </Step>

  <Step title="Configure the MCP client">
    Add a logo, name and description to your MCP client. Leave the headers in step 3 empty and click on **+ Add connection** in step 4.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_configure_mcp_client.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=778876fc7bf0e484d936c525db1062ea" alt="Configure MCP client with Qontext URL" className="rounded-lg" width="1490" height="1765" data-path="ai-tools/images/langdock/langdock_configure_mcp_client.png" />
  </Step>

  <Step title="Allow Qontext access">
    When prompted, complete the OAuth flow: log in to Qontext and allow Langdock to access your Qontext account.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_allow_access.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=d14e8e3edc4937c5ec45f23153130bb2" alt="Allow Qontext access in OAuth" className="rounded-lg" style={{ maxWidth: '50%' }} width="888" height="1224" data-path="ai-tools/images/langdock/langdock_allow_access.png" />

    Your connection should now test successfully. Make sure to select the retrieval tool to add it to your Langdock actions and save the configurations.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_mcp_client_tools.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=816a059b890f8084d8a666e8b6557463" alt="Qontext MCP tools in Langdock" className="rounded-lg" style={{ maxWidth: '100%' }} width="1478" height="919" data-path="ai-tools/images/langdock/langdock_mcp_client_tools.png" />
  </Step>

  <Step title="Trigger Qontext in a new chat">
    Open a new chat in Langdock and type **@Qontext** and select the Qontext integration and send your first prompt to it.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_trigger_qontext.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=219f0d1cf3aea61014aa0f8d1f58e285" alt="Trigger Qontext in Langdock Chat" className="rounded-lg" style={{ maxWidth: '100%' }} width="1605" height="1121" data-path="ai-tools/images/langdock/langdock_trigger_qontext.png" />

    This will trigger the retrieval tool. To continue, select the correct connection and **confirm**.

    <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_chat_with_qontext.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=15a7318c15adad58023208159852a03c" alt="Chat with Qontext context" className="rounded-lg" style={{ maxWidth: '100%' }} width="1544" height="720" data-path="ai-tools/images/langdock/langdock_chat_with_qontext.png" />
  </Step>
</Steps>

<div className="qontext-tip-check-wrapper">
  <Check>
    Once connected, Qontext is available across Langdock Chat, Agent, and Workflows. You can use it in any of the three modes described below.
  </Check>
</div>

***

## Using Qontext in Langdock

If you haven't set up Qontext in Langdock yet, refer to the [Installation](#installation) steps above.

Qontext works in all three Langdock surfaces: **Chat**, **Agent**, and **Workflow**.

<Tabs>
  <Tab title="Chat">
    #### Chat

    In **Chat**, you can retrieve context in a direct conversation so you always get answers based on up-to-date company context.

    <Steps>
      <Step title="Start or open a chat in Langdock." />

      <Step title="Trigger Qontext (@Qontext) when you need company context.">
        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_trigger_qontext.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=219f0d1cf3aea61014aa0f8d1f58e285" alt="Trigger Qontext in Langdock Chat" className="rounded-lg" style={{ maxWidth: '100%' }} width="1605" height="1121" data-path="ai-tools/images/langdock/langdock_trigger_qontext.png" />
      </Step>

      <Step title="Enter your prompt to retrieve relevant information from Qontext." />
    </Steps>
  </Tab>

  <Tab title="Agent">
    #### Agent

    Add the **Qontext retrieval tool** as an action to your agent. Once added, the agent can automatically retrieve relevant context from your connected vault when users chat with it.

    <Steps>
      <Step title="Open the Agent configurator and create or edit an agent.">
        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_customer_support_agent.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=1cb522c1ceb4797384ba3adabc1a2496" alt="Add or edit agent" className="rounded-lg" style={{ maxWidth: '100%' }} width="1234" height="1380" data-path="ai-tools/images/langdock/langdock_customer_support_agent.png" />
      </Step>

      <Step title="In the Actions section, click + Add action.">
        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_agent_add_action.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=35edcba4c91e5ebf48e4848f064196e0" alt="Add Qontext retrieval tool as action to agent" className="rounded-lg" style={{ maxWidth: '100%' }} width="1188" height="549" data-path="ai-tools/images/langdock/langdock_agent_add_action.png" />

        Search for the retrieval action from the Qontext integration and select it.

        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_agent_retrieval_tool.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=4693acf753c0f638f4d80866691458df" alt="Qontext retrieval tool in agent" className="rounded-lg" style={{ maxWidth: '100%' }} width="1550" height="503" data-path="ai-tools/images/langdock/langdock_agent_retrieval_tool.png" />
      </Step>

      <Step title="When users chat with this agent, it will now retrieve relevant context from your connected vault." />
    </Steps>
  </Tab>

  <Tab title="Workflow">
    #### Workflow

    In **Workflow**, you can either use an **Agent** node that has the Qontext retrieval tool as an action, or add the retrieval tool directly as a node.

    <Steps>
      <Step title="Create or edit a workflow in Langdock." />

      <Step title="Add an Agent using the Qontext retrieval tool as an action or add the tool directly as a workflow node to the canvas. Connect it to your trigger or previous steps.">
        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_workflow_new.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=28183bce25a41e4edc0eb310821fa42e" alt="Langdock workflow with agent" className="rounded-lg" style={{ maxWidth: '100%' }} width="2854" height="590" data-path="ai-tools/images/langdock/langdock_workflow_new.png" />
      </Step>

      <Step title="Ensure the correct connection is selected for the retrieval tool. Then, knowledge from your vault can be retrieved in the workflow.">
        <img src="https://mintcdn.com/qontext/QlZIaBHl38HWuxBz/ai-tools/images/langdock/langdock_workflow_connection.png?fit=max&auto=format&n=QlZIaBHl38HWuxBz&q=85&s=171fb4ec81450e85aff877e836f66c85" alt="Langdock workflow connection" className="rounded-lg" style={{ maxWidth: '100%' }} width="2897" height="1729" data-path="ai-tools/images/langdock/langdock_workflow_connection.png" />
      </Step>
    </Steps>
  </Tab>
</Tabs>

***

### Example prompts

```text theme={null}
@Qontext. What were the key takeaways from last week's sales meeting?
```

```text theme={null}
Summarize what we know about Acme Corp. @Qontext.
```

```text theme={null}
@Qontext. Find our pricing guidelines and help me draft a proposal.
```

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="Qontext doesn't appear in my integrations. What can I do?">
    Ensure the MCP client is configured with the correct URL (`https://api.qontext.ai/mcp`) and that you have saved and enabled the Qontext tools. Restart or refresh Langdock if needed.
  </Accordion>

  <Accordion title="The URL is not shown when triggering Qontext for the first time.">
    Ask specifically for the URL to access your Qontext vault in the chat. If this does not work, start a new chat and repeat.
  </Accordion>

  <Accordion title="Agent or workflow doesn't use Qontext">
    In the agent configurator, confirm that the Qontext action is added to the agent and that a connection (and workspace) is selected. In workflows, check that the agent node is configured to use the Qontext integration. Include in the prompt to use the retrieval tool.
  </Accordion>
</AccordionGroup>

***

## Need help?

If you encounter issues with the Langdock integration, reach out at [support@qontext.ai](mailto:support@qontext.ai).