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

# Connect to RTLCA

> Wire your AI client to the Real-Time LCA MCP server

Pick your client below. Every client connects to the same hosted endpoint
(`https://mcp.realtimelca.com/mcp`) and authenticates with your Real-Time
LCA account via OAuth — no API key, no token to paste.

<Note>
  Using **Autodesk Forma** or **Revit** tools? See
  [Connect to RTLCA × Autodesk](/ai-tools/autodesk-mcp) — it uses a
  different endpoint and requires an Autodesk account + active Forma hub.
</Note>

<Tabs>
  <Tab title="Claude.ai">
    Connect the Claude web app at [claude.ai](https://claude.ai). Works in
    any browser — no Claude Desktop install required.

    ### Prerequisites

    * Claude account
    * Real-Time LCA account
    * On **Team** or **Enterprise** plans, you need to be an **admin** to
      add servers

    <Steps>
      <Step title="Open the Connectors page">
        Go to [claude.ai/customize/connectors](https://claude.ai/customize/connectors).
      </Step>

      <Step title="Add a custom connector">
        Click the **+** sign → **Add custom connector**. Paste the URL:

        ```
        https://mcp.realtimelca.com/mcp
        ```
      </Step>

      <Step title="Authenticate the MCP server">
        Complete any authentication steps Claude prompts for, signing in with your Real-Time LCA account.
      </Step>

      <Step title="Mention RTLCA in a chat">
        The next time you mention **RTLCA** in a chat, Claude will detect
        the connector and ask you for permission to execute tools.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Desktop">
    Connect the Claude Desktop app. The flow is the same as
    [Claude.ai](#claude-ai) — done through the in-app **Connectors** UI,
    not a config file.

    ### Prerequisites

    * Claude Desktop installed (macOS or Windows)
    * Real-Time LCA account
    * On **Team** or **Enterprise** plans, you need to be an **admin** to
      add servers

    <Steps>
      <Step title="Open the Connectors page">
        In Claude Desktop, open **Settings → Connectors**.
      </Step>

      <Step title="Add a custom connector">
        Click the **+** sign → **Add custom connector**. Paste the URL:

        ```
        https://mcp.realtimelca.com/mcp
        ```
      </Step>

      <Step title="Authenticate the MCP server">
        Complete any authentication steps Claude prompts for, signing in
        with your Real-Time LCA account.
      </Step>

      <Step title="Mention RTLCA in a chat">
        The next time you mention **RTLCA** in a chat, Claude will detect
        the connector and ask you for permission to execute tools.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Code">
    ### Prerequisites

    * Node.js ≥ 18
    * Claude Code installed (`npm install -g @anthropic-ai/claude-code`)
    * A Real-Time LCA account

    <Steps>
      <Step title="Run the add command">
        A single command in your terminal:

        ```bash theme={null}
        claude mcp add realtimelca --transport http https://mcp.realtimelca.com/mcp
        ```
      </Step>

      <Step title="Authenticate on first use">
        Claude Code will prompt you to authenticate the first time you use a
        `realtimelca` tool. Follow the link to sign in with your RTLCA
        account; the token is cached for later calls.
      </Step>

      <Step title="Try a first prompt">
        Start a session and ask, for example:

        ```
        List all my building projects
        ```

        ```
        Show me the GWP dashboard for the project named "Aalborg Office"
        ```
      </Step>
    </Steps>
  </Tab>

  <Tab title="Codex">
    ### Prerequisites

    * Codex app
    * A Real-Time LCA account — you'll sign in via the browser

    <Steps>
      <Step title="Open Codex">
        Launch the Codex app.
      </Step>

      <Step title="Open the config file">
        Go to **Settings → Configurations → Open `config.toml`**.
      </Step>

      <Step title="Add the rtlca MCP server">
        Paste the following at the very top of `config.toml`:

        ```toml theme={null}
        mcp_oauth_callback_port = 5555

        [mcp_servers.rtlca]
        url = "https://mcp.realtimelca.com/mcp"
        ```
      </Step>

      <Step title="Restart Codex">
        Quit Codex completely — make sure the process is no longer running — then start it again.
      </Step>

      <Step title="Authenticate">
        Go to **Settings → MCP Servers**. The `rtlca` connection should now be listed.

        Click **Authenticate**. A browser window opens; sign in with your Real-Time LCA credentials, then return to Codex.
      </Step>

      <Step title="Try a first prompt">
        Start a chat and ask, for example:

        <Prompt description="What projects do I have in RTLCA?" icon="folder">
          What projects do I have in RTLCA?
        </Prompt>
      </Step>
    </Steps>
  </Tab>

  <Tab title="Cursor">
    ### Prerequisites

    * Cursor installed ([cursor.com](https://cursor.com/))
    * Real-Time LCA account

    <Steps>
      <Step title="Open Cursor's MCP settings">
        In Cursor, go to **Settings → Tools & MCP** and select
        **New MCP Server**. `mcp.json` opens for editing.
      </Step>

      <Step title="Add the realtimelca MCP server">
        ```json theme={null}
        {
          "mcpServers": {
            "realtimelca": {
              "url": "https://mcp.realtimelca.com/mcp"
            }
          }
        }
        ```

        Save the file.
      </Step>

      <Step title="Click Connect to authenticate">
        Cursor lists the server as **Needs authentication**. Click the
        **Connect** button — your browser opens to the Real-Time LCA
        sign-in page. Sign in; the token returns to Cursor automatically.
      </Step>

      <Step title="Try a first prompt">
        Open a new chat and ask, for example:

        ```
        List all my building projects
        ```
      </Step>
    </Steps>
  </Tab>

  <Tab title="ChatGPT">
    Real-Time LCA is published on the [ChatGPT App Store](https://chatgpt.com/apps/real-time-lca-mcp-server/asdk_app_69f0459f7b508191a7cc3188d4f1a2ff) — install it in a couple of clicks, no custom connector required.

    ### Prerequisites

    * A ChatGPT account
    * A Real-Time LCA account — you'll sign in via the browser

    <Steps>
      <Step title="Open the app listing">
        Go to the [Real-Time LCA MCP Server listing](https://chatgpt.com/apps/real-time-lca-mcp-server/asdk_app_69f0459f7b508191a7cc3188d4f1a2ff) on the ChatGPT App Store, then click **Connect** in the top right.

        <Frame caption="Real-Time LCA MCP Server on the ChatGPT App Store">
          <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=48185df921affb412375efaf88d1f277" alt="ChatGPT App Store listing for the Real-Time LCA MCP Server with a Connect button in the top right." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store.png" />
        </Frame>
      </Step>

      <Step title="Add to ChatGPT">
        In the **Add Real-Time LCA MCP Server to ChatGPT** dialog, click **Sign in with Real-Time LCA MCP Server**.

        <Frame caption="Add Real-Time LCA MCP Server to ChatGPT dialog">
          <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20Sign%20In.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=39fa0b09f4479a458d37614aeb5a76bb" alt="ChatGPT modal asking the user to add the Real-Time LCA MCP Server, with a Sign in button." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - Sign In.png" />
        </Frame>
      </Step>

      <Step title="Sign in with your RTLCA account">
        A browser window opens to the Real-Time LCA sign-in page. Sign in with your RTLCA credentials, then return to ChatGPT.

        <Frame caption="Real-Time LCA sign-in page">
          <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20Credentials.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=fa1d203c37c74ad9666808b5e281f094" alt="Real-Time LCA sign-in page with Email and Password fields." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - Credentials.png" />
        </Frame>
      </Step>

      <Step title="Confirm the connection">
        ChatGPT confirms with a **Real-Time LCA MCP Server is now connected.** banner, and the **Connect** button changes to **Start chat**.

        <Frame caption="Connection confirmation in ChatGPT">
          <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20Connected.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=31500a5b179a582dbe42017a59b1fd68" alt="ChatGPT App Store listing showing a green Real-Time LCA MCP Server is now connected banner and a Start chat button." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - Connected.png" />
        </Frame>
      </Step>

      <Step title="Try a first prompt">
        Click **Start chat** and ask, for example:

        ```
        List all my building projects
        ```
      </Step>
    </Steps>

    ### Manage or review the connection

    Open the gear icon next to **Start chat** on the listing, or go to **Settings → Apps → Real-Time LCA MCP Server** from anywhere in ChatGPT.

    <Frame caption="Open the connection settings via the gear icon">
      <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20Go%20to%20Settings.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=2d63063e8fe1472af900f9732edf4dcc" alt="Real-Time LCA MCP Server listing in ChatGPT with a Start chat button and a gear icon to open settings." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - Go to Settings.png" />
    </Frame>

    From here you can toggle **Reference memories and chats**, review the connection details, or **Disconnect** the app.

    <Frame caption="Apps → Real-Time LCA MCP Server settings">
      <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20Settings.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=ca81965c79e6a2f3ac1d5d243d5aed67" alt="ChatGPT Apps settings showing Real-Time LCA MCP Server with Disconnect, Preferences, and Information sections." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - Settings.png" />
    </Frame>

    Scroll down to **Actions** for the full list of MCP tools the app exposes and the scopes each one needs.

    <Frame caption="Actions exposed by the Real-Time LCA MCP Server">
      <img src="https://mintcdn.com/real-timelca/I6uHdy68CPzNdzhH/images/user-guide/OpenAI%20ChatGPT%20App%20Store%20-%20MCP%20Tools%20-%20Actions.png?fit=max&auto=format&n=I6uHdy68CPzNdzhH&q=85&s=74a3024d8ce32bc8df4a659baa833861" alt="Actions panel listing rtlca_create_construction, rtlca_create_epd, and other Real-Time LCA MCP tools with their required scopes." width="2240" height="2736" data-path="images/user-guide/OpenAI ChatGPT App Store - MCP Tools - Actions.png" />
    </Frame>
  </Tab>

  <Tab title="Mistral Le Chat">
    Create the connector in **AI Studio**, then attach it to any chat in
    [Le Chat](https://chat.mistral.ai).

    ### Prerequisites

    * Mistral plan with MCP connector support
    * Real-Time LCA account

    <Steps>
      <Step title="Open AI Studio Connectors">
        In AI Studio, go to **Connectors → Add Connector**.
      </Step>

      <Step title="Fill in the connector">
        * **Name**: any (e.g. `Real-Time LCA`)
        * **Server URL**: `https://mcp.realtimelca.com/mcp`
        * **Workspace**: `Private`

        Click **Create**.
      </Step>

      <Step title="Sign in with your RTLCA account">
        Creating the connector opens a browser window to the Real-Time LCA
        sign-in page. Sign in; once successful you're redirected back to
        AI Studio.
      </Step>

      <Step title="Use the connector in Le Chat">
        Start a new chat in [Le Chat](https://chat.mistral.ai). Click the
        **+** symbol, open the **Connectors** tab, and select the RTLCA
        connector. Then prompt, for example:

        ```
        List all my building projects
        ```
      </Step>
    </Steps>
  </Tab>

  <Tab title="LM Studio">
    Run a local LLM via [LM Studio](https://lmstudio.ai/) and connect it
    to the RTLCA MCP server — no Claude or other subscription required,
    no token limits, no chat data leaving your machine.

    ### Prerequisites

    * LM Studio installed ([lmstudio.ai](https://lmstudio.ai/))
    * A locally downloaded model that supports tool / function calling
    * A Real-Time LCA account

    <Steps>
      <Step title="Install LM Studio">
        Download and install LM Studio from
        [lmstudio.ai](https://lmstudio.ai/). Launch the app once
        installation completes.
      </Step>

      <Step title="Load a local model">
        In the **Discover** tab, download a tool-capable model, then load
        it from the **Chat** tab's model selector. **Recommended:**
        `Gemma 4` or `Qwen 3.5` — go larger if your machine can run it.
        When loading, increase the context size to **at least 15k** —
        the MCP tool responses need the headroom.
      </Step>

      <Step title="Add the RTLCA MCP server">
        Open LM Studio's **Program** / **MCP** panel and edit `mcp.json`:

        ```json theme={null}
        {
          "mcpServers": {
            "rtlca-mcp-server": {
              "url": "https://mcp.realtimelca.com/mcp"
            }
          }
        }
        ```

        Save the file. LM Studio will pick up the new server and list its
        tools.
      </Step>

      <Step title="Click Authenticate in LM Studio">
        Once the server is in `mcp.json`, LM Studio shows an
        **Authenticate** button on the `rtlca-mcp-server` entry. Click it
        — your default browser opens to the Real-Time LCA sign-in page.
        Sign in with your RTLCA credentials; LM Studio receives the token
        automatically.
      </Step>

      <Step title="Chat with the connected model">
        Back in LM Studio's Chat tab, ask:

        ```
        List all my building projects
        ```
      </Step>
    </Steps>

    <Note>
      Tool-calling quality varies a lot between local models. If the
      model ignores the available tools or hallucinates arguments, try a
      larger variant or one explicitly tuned for function calling.
    </Note>
  </Tab>
</Tabs>