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

# Integrated MCP Server

> Use the built-in Model Context Protocol server to let AI assistants directly control tools for device management, AI models, projects, and more.

The Qualcomm VS Code Extension ships with an **embedded MCP (Model Context Protocol) server** that starts automatically when the extension loads. AI coding assistants such as Claude, Codex, Cursor, GitHub Copilot, etc. can connect to it over `localhost` and invoke a structured tool call — no manual configuration required.

<img src="https://mintcdn.com/qualcomm-prod/fI394-r7UzwPirkn/Tools/QVSCE/images/mcp_server_running.png?fit=max&auto=format&n=fI394-r7UzwPirkn&q=85&s=68e29e1272b97b41f018e7ec29d36851" alt="MCP Server running indicator in the extension sidebar" width="1438" height="800" data-path="Tools/QVSCE/images/mcp_server_running.png" />

<Info>
  The MCP server runs entirely on your local machine. No data leaves your device
  through the MCP channel; all tool calls go to `127.0.0.1` only.
</Info>

***

## How It Works

When enabled, the extension starts an HTTP server on `localhost`.

```
http://127.0.0.1:3100/mcp
```

<img src="https://mintcdn.com/qualcomm-prod/fI394-r7UzwPirkn/Tools/QVSCE/images/mcp_server_status.png?fit=max&auto=format&n=fI394-r7UzwPirkn&q=85&s=54621e35b6fd4ad6700c7c4390393246" alt="MCP Server: Running status shown in the extension sidebar navigation" width="1014" height="449" data-path="Tools/QVSCE/images/mcp_server_status.png" />

***

## Configuration

The sidebar shows **MCP Server: Running (port 3100)** when active. Click this label to open the MCP & C++ RAG settings directly.

Alternatively, Open VS Code Settings and search for `@id:qvsce.mcpServer.enabled @id:qvsce.mcpServer.port @id:qvsce.cppRag.samplesDir` to see all three MCP-related settings in one view.

<img src="https://mintcdn.com/qualcomm-prod/fI394-r7UzwPirkn/Tools/QVSCE/images/mcp_server_settings.png?fit=max&auto=format&n=fI394-r7UzwPirkn&q=85&s=22ef1e2db700a60539925cea64153d47" alt="VS Code Settings panel showing QVSCE MCP server configuration options" width="1157" height="514" data-path="Tools/QVSCE/images/mcp_server_settings.png" />

| Setting                   | Default   | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
| ------------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `qvsce.mcpServer.enabled` | `true`    | Enable or disable the embedded MCP server. Changes take effect immediately — no window reload needed.                                                                                                                                                                                                                                                                                                                                                                                                  |
| `qvsce.mcpServer.port`    | `3100`    | Port the HTTP server listens on (1–65535). Change this if port 3100 conflicts with another process.                                                                                                                                                                                                                                                                                                                                                                                                    |
| `qvsce.cppRag.samplesDir` | *(empty)* | Absolute path to a directory of C/C++ source files (`.cpp`, `.cc`, `.cxx`, `.h`, `.hpp`, `.hxx`) representing your preferred coding style, SDK-specific patterns, or domain-specific application code — for example, internal SDK wrapper libraries, team utility code, or reference applications. All matching files in subdirectories are discovered recursively. After setting this path, call `build_cpp_rag_index` to populate the index. Leave empty to rely on the built-in default index only. |

<Tip>
  After changing the port, any MCP client configuration pointing to the old port
  (e.g., a `claude_desktop_config.json` entry) must be updated to match.
</Tip>

### Connecting an AI Client

Any MCP-compatible AI assistant can connect to the server. The general pattern is the same across clients: point it at `http://127.0.0.1:3100/mcp` using the **Streamable HTTP** transport.

<Steps>
  <Step title="Confirm the server is running">
    Check the extension sidebar for **MCP Server: Running (port 3100)**. If it shows Stopped, enable it in Settings (`qvsce.mcpServer.enabled`).
  </Step>

  <Step title="Configure your AI client">
    Add the server endpoint to your client's MCP configuration. See the examples below for Claude and Codex — other clients follow the same pattern.

    <Tabs>
      <Tab title="Claude Desktop / Claude Code">
        Add to `claude_desktop_config.json` (Claude Desktop) or `.claude/mcp.json` (Claude Code in a project):

        ```json theme={null}
        {
          "mcpServers": {
            "qualcomm-ide": {
              "url": "http://127.0.0.1:3100/mcp"
            }
          }
        }
        ```

        In **Claude Code** you can also add it from the terminal:

        ```bash theme={null}
        claude mcp add qualcomm-ide --transport http http://127.0.0.1:3100/mcp
        ```
      </Tab>

      <Tab title="Codex CLI">
        Add to `~/.codex/config.toml` or pass inline:

        ```toml theme={null}
        [[mcp_servers]]
        name = "qualcomm-ide"
        url  = "http://127.0.0.1:3100/mcp"
        ```

        Or pass it as a flag when running Codex:

        ```bash theme={null}
        codex --mcp-server "qualcomm-ide=http://127.0.0.1:3100/mcp"
        ```
      </Tab>

      <Tab title="Other clients">
        Any client that supports the MCP Streamable HTTP transport can connect. Use:

        * **URL:** `http://127.0.0.1:3100/mcp`
        * **Transport:** Streamable HTTP (session-based)
        * **Auth:** None — local-only, no credentials required

        Consult your client's documentation for where to add MCP server entries.
      </Tab>
    </Tabs>
  </Step>

  <Step title="Verify the connection">
    Ask your assistant: *"List my connected Qualcomm devices."* A response with device information confirms the server is reachable and tools are available.
  </Step>
</Steps>

***

## Available Tools

The server exposes tools across nine functional categories. The tool set continues to evolve — to see the latest available tools, ask your AI assistant: *"What MCP tools are available from the Qualcomm IDE?"* Click a category below to jump to its tool reference. Tools marked **Linux-only** are unavailable on Windows-native VS Code (WSL remote connections are supported).

<CardGroup cols={2}>
  <Card title="Device Management" icon="mobile" href="#device-management">
    *"What devices are connected right now?"*

    *"Connect to my device over SSH at 192.168.1.42 as root."*

    *"Flash the latest Qualcomm Linux image onto my active device."*

    *"Scan for Wi-Fi networks on my device and connect it to my network."*
  </Card>

  <Card title="Projects" icon="folder" href="#projects">
    *"Build my project and deploy it to the connected device."*

    *"Create a new C++ application project using the installed SDK."*

    *"Import the GStreamer sample project from my SDK."*

    *"Register my existing project at \~/myapp with the installed SDK."*
  </Card>

  <Card title="C++ Code Search" icon="search" href="#c-code-search-rag">
    *"Find C++ sample code for initializing a camera pipeline."*

    *"Show me examples of camera sensor initialization from the SDK samples."*

    *"How do I set up a GStreamer source element? Find relevant samples."*
  </Card>

  <Card title="Documentation" icon="book" href="#documentation-search">
    *"How do I flash a device using the extension?"*

    *"What are the prerequisites for building a project?"*

    *"Explain how SSH key-based authentication is set up for a device."*
  </Card>

  <Card title="AI Models" icon="brain" href="#ai-models">
    *"Download the Llama 3 model for my RB3 Gen 2 device."*

    *"Profile the ResNet50 model on my connected device and show me the results."*

    *"Compile the Whisper model for my device and push it once done."*

    *"What AI models are available for the RB5 platform?"*
  </Card>

  <Card title="SDKs & OS Images" icon="box" href="#sdks-and-os-images">
    *"What SDKs are available for my devkit?"*

    *"Download the latest OS image and SDK for my RB3 Gen 2 in one go."*

    *"Is my SDK download finished yet?"*
  </Card>

  <Card title="Skills Hub" icon="puzzle" href="#skills-hub">
    *"What skills are available for my connected device?"*

    *"Install the best skill for working with GStreamer pipelines."*

    *"Show me the documentation for the camera-capture skill."*
  </Card>

  <Card title="Overlay Configuration" icon="layer-group" href="#overlay-configuration">
    *"What overlay configurations are available on my device?"*

    *"Switch my device to the upstream overlay configuration."*
  </Card>

  <Card title="Delta Flash" icon="bolt" href="#delta-flash-incremental-deploy">
    *"Show me which files would change if I did an incremental deploy now."*

    *"Sync only the changed build artifacts to my device over SSH."*

    *"Do a dry run of the delta flash and then apply it if it looks right."*
  </Card>
</CardGroup>

***

### Device Management

These tools give AI assistants full visibility and control over connected Qualcomm hardware. Most other tool categories depend on an active device being selected first.

<AccordionGroup>
  <Accordion title="list_devices — List all connected devices">
    Returns every device currently detected by the extension, including serial
    numbers, connection type (SSH or EDL), and device state.
  </Accordion>

  <Accordion title="get_active_device — Get the selected device">
    Returns details about the device currently set as active. Most other device
    and project tools operate on this device implicitly.
  </Accordion>

  <Accordion title="select_device — Set the active device">
    Sets a device as active by serial number. If the serial number is omitted or
    not found, an interactive VS Code picker is shown.
  </Accordion>

  <Accordion title="add_device_via_ssh — Add a device over SSH">
    Adds a new device to the known list using an SSH connection. Can generate a
    new SSH key pair; prompts securely for the device password when needed.
  </Accordion>

  <Accordion title="validate_ssh_connection — Check SSH reachability">
    Verifies that the SSH connection to a device is reachable without performing
    any other operations.
  </Accordion>

  <Accordion title="update_ssh_config — Edit SSH configuration">
    Updates the SSH connection parameters (host, port, user, key) for the active
    device.
  </Accordion>

  <Accordion title="list_wifi_networks / connect_wifi / disconnect_wifi / get_wifi_status — Wi-Fi management">
    Scans, connects, disconnects, and inspects Wi-Fi on connected devices over
    SSH.
  </Accordion>

  <Accordion title="reboot_device — Reboot a device">
    Reboots the active device normally or into EDL (Emergency Download) mode.
    EDL reboots require explicit destructive confirmation.
  </Accordion>

  <Accordion title="flash_device_software — Flash an OS image (Linux-only)">
    Flashes an OS image onto the active device. Streams real-time stage
    notifications: EDL wait, flashing progress, and CamX overlay pending status.
  </Accordion>

  <Accordion title="apply_camx_overlay — Apply CamX overlay (Linux-only)">
    Applies the CamX proprietary overlay after `flash_device_software` signals
    it is awaiting the overlay step. Requires Qualcomm Linux Proprietary v2.0+.
  </Accordion>

  <Accordion title="list_devkit_catalog — Browse supported devkits">
    Returns all supported Qualcomm devkits with IDs, chipsets, supported OS
    versions, and host architectures.
  </Accordion>

  <Accordion title="get_pre_flash_data — Pre-flash instructions">
    Retrieves the pre-flash instructions URL for a given devkit and target OS
    combination.
  </Accordion>

  <Accordion title="get_auto_activate_status / update_auto_activate — Auto-activation control">
    Reads and sets whether the extension automatically selects a device when one
    is connected.
  </Accordion>

  <Accordion title="reset_device_selection — Clear the active device">
    Clears the active device selection and resets the auto-activation state.
  </Accordion>

  <Accordion title="remove_device — Remove a known device">
    Removes a device from the known device list. Requires destructive
    confirmation.
  </Accordion>

  <Accordion title="provision_ufs / program_cdt — Low-level provisioning (Linux-only)">
    **provision\_ufs**: Provisions Universal Flash Storage on the device in EDL
    mode. **program\_cdt**: Programs the Configuration Data Table. Both require
    EDL mode and destructive confirmation.
  </Accordion>
</AccordionGroup>

***

### Projects

Build, deploy, and run applications directly from an AI conversation. The full workflow — from project creation to on-device execution — is available as tool calls.

<AccordionGroup>
  <Accordion title="build_project — Build (Linux-only)">
    Runs the `qvsce-build` task. Supports a headless mode that accepts
    `projectPath` and `sdkId` directly — no open VS Code window required.
  </Accordion>

  <Accordion title="deploy_project — Build and deploy (Linux-only)">
    Builds the project and deploys the binary to the active device via
    SSH. Supports headless mode.
  </Accordion>

  <Accordion title="run_project — Run on-device (Linux-only)">
    Executes the deployed application on the active device. Supports headless
    mode.
  </Accordion>

  <Accordion title="import_sample_project — Import from SDK (Linux-only)">
    Imports a sample project from an installed SDK into the VS Code workspace,
    including source and build dependencies.
  </Accordion>

  <Accordion title="create_project — New project from template (Linux-only)">
    Creates a new C/C++ Application or GStreamer Plugin Application from an SDK
    template, then configures `.vscode` with `tasks.json`, `launch.json`, and
    `c_cpp_properties.json`.
  </Accordion>

  <Accordion title="register_project — Register an existing project">
    Associates an existing local project with an installed SDK and writes the
    `.vscode` configuration files needed to build and debug it.
  </Accordion>

  <Accordion title="update_preferred_sdk — Switch the active SDK">
    Sets or refreshes the SDK used by the workspace for compilation and
    deployment.
  </Accordion>
</AccordionGroup>

***

### C++ Code Search (RAG)

The extension maintains a local TF-IDF index of C++ code samples that AI assistants query automatically when writing or explaining code.

<AccordionGroup>
  <Accordion title="search_cpp_samples — Search for C++ code">
    Searches the index using TF-IDF similarity against a natural-language or
    code query. Returns up to 10 function-level code chunks with relevance
    scores.
  </Accordion>

  <Accordion title="build_cpp_rag_index — Build the search index">
    Builds or rebuilds the C++ code search index from the directory set in
    `qvsce.cppRag.samplesDir`. A built-in default index is always present; user
    samples are merged on top. Returns the total chunk and vocabulary counts on
    completion.
  </Accordion>

  <Accordion title="get_cpp_rag_stats — Index statistics">
    Returns the total chunk count, vocabulary size, default chunk count, and
    user chunk count for the current index.
  </Accordion>
</AccordionGroup>

<Note>
  The index is built and stored entirely on your local machine — no source code
  or index data is transmitted externally. If multiple developers on a team need
  the same coding conventions reflected in their agent's suggestions, each
  developer must configure `qvsce.cppRag.samplesDir` and run
  `build_cpp_rag_index` individually. Teams can share the same source directory
  (for example, via a shared repository) to achieve consistent results, but the
  index build must be performed locally by each developer.
</Note>

***

### Documentation Search

The assistant calls these tools automatically — on tool failures, before complex operations, and whenever you ask about IDE features.

<AccordionGroup>
  <Accordion title="search_documentation — Search IDE docs">
    Searches the Qualcomm DragonWing IDE documentation via the external docs
    server. Called automatically on tool failures, before complex multi-step
    operations, and whenever you ask about IDE features.
  </Accordion>

  <Accordion title="get_documentation — Retrieve a specific page">
    Fetches a documentation page or resource by URI from the DragonWing docs
    server.
  </Accordion>
</AccordionGroup>

***

### AI Models

Full integration with Qualcomm AI Hub for cloud profiling and compilation, plus local on-device benchmarking.

<AccordionGroup>
  <Accordion title="list_ai_model_catalog — Browse the AI Hub catalog">
    Lists AI models available for download, with optional filters for device
    name and model type (LLM, vision, audio, etc.).
  </Accordion>

  <Accordion title="download_ai_model — Download a model">
    Downloads an AI model from the catalog. Fetches available precision/runtime
    variants first; an interactive picker appears if a variant is not specified.
  </Accordion>

  <Accordion title="get_ai_model_status — Model status overview">
    Returns the current download, compile, and flash status of all models in the
    local cache.
  </Accordion>

  <Accordion title="push_ai_model_to_device — Flash a model to hardware">
    Pushes a downloaded model to the active device as a background operation.
  </Accordion>

  <Accordion title="profile_ai_model — Cloud profiling via AI Hub">
    Submits a profiling job to Qualcomm AI Hub for a specified device. Returns a
    job reference for polling.
  </Accordion>

  <Accordion title="local_profile_ai_model — On-device profiling">
    Runs a profiling job directly on the active device — measures real inference
    time and memory usage on hardware.
  </Accordion>

  <Accordion title="get_ai_model_profile_result / get_ai_model_local_profile_result — Retrieve results">
    Polls profiling job results keyed by model UID — cloud or on-device.
  </Accordion>

  <Accordion title="compile_ai_model — Compile and customize a model">
    Compiles a model via AI Hub for a specific device target, with optional
    precision and optimization settings.
  </Accordion>

  <Accordion title="get_ai_model_benchmark — Benchmarking data">
    Returns inference time, memory usage, layer counts, and tool versions for a
    model. Filterable by device, precision, and runtime.
  </Accordion>

  <Accordion title="import_ai_model — Import a local model file">
    Imports a model file already on disk into the extension's model cache.
  </Accordion>

  <Accordion title="remove_ai_model — Remove a model">
    Removes a previously downloaded model from the local cache. Requires
    destructive confirmation.
  </Accordion>

  <Accordion title="list_ai_model_device_types — Supported device types">
    Returns all device types that support AI Hub profiling and compilation jobs.
  </Accordion>
</AccordionGroup>

***

### SDKs and OS Images

Typically used once during environment setup — browse catalogs, download, and install the SDK and OS image for your devkit.

<AccordionGroup>
  <Accordion title="download_devkit_software — Bundle download">
    Downloads both an OS image and an SDK in a single tool call. Either
    component can be omitted.
  </Accordion>

  <Accordion title="list_sdk_catalog — Browse available SDKs">
    Lists SDKs for a given devkit and OS version: names, IDs, host
    architectures, versions, and download URLs.
  </Accordion>

  <Accordion title="download_sdk / get_sdk_status / install_sdk — SDK lifecycle">
    **download\_sdk**: Starts a background SDK download. **get\_sdk\_status**:
    Polls progress and install path. **install\_sdk**: Installs a downloaded SDK
    (Linux-only).
  </Accordion>

  <Accordion title="list_os_image_catalog — Browse OS images">
    Lists OS images for a devkit: names, IDs, versions, and download metadata.
  </Accordion>

  <Accordion title="download_os_image / get_os_image_status — OS image download">
    **download\_os\_image**: Starts a background OS image download.
    **get\_os\_image\_status**: Polls progress and flags CamX overlay requirements.
  </Accordion>
</AccordionGroup>

***

### Skills Hub

Browse and install agent skills that extend what AI assistants can do with the extension.

<AccordionGroup>
  <Accordion title="search_skills — Find relevant skills">
    Searches skills by name, description, and tags using weighted matching.
    Automatically filters by the connected device's environment.
  </Accordion>

  <Accordion title="download_skill — Install a skill">
    Installs a skill into the selected agent's user skills directory (Claude,
    Cursor, or Codex).
  </Accordion>

  <Accordion title="get_skill_documentation — Read a skill's SKILL.md">
    Returns the full documentation for a single catalog skill, defaulting to the
    version best matched for the connected environment.
  </Accordion>

  <Accordion title="list_skills — Full catalog">
    Lists every skill from all configured repositories, including all published
    versions and per-version compatibility metadata.
  </Accordion>

  <Accordion title="delete_skill — Uninstall a skill">
    Removes a previously installed skill from the agent's skills directory.
  </Accordion>

  <Accordion title="refresh_skills_catalog — Force catalog refresh">
    Bypasses the catalog TTL and re-fetches all configured skill repositories
    immediately.
  </Accordion>
</AccordionGroup>

***

### Overlay Configuration

Advanced configuration for Qualcomm Linux devices — inspect and switch device overlays over SSH.

<AccordionGroup>
  <Accordion title="get_overlay_configuration — Read overlay options">
    Returns available overlay categories, the currently active overlay, and
    upstream/downstream options for the active device. Qualcomm Linux only.
  </Accordion>

  <Accordion title="apply_overlay_configuration — Apply overlay selections">
    Applies a chosen set of overlay selections to the active device via SSH.
    Qualcomm Linux only.
  </Accordion>
</AccordionGroup>

***

### Delta Flash (Incremental Deploy)

Incrementally sync build artifacts to a device over SSH — faster than a full reflash when only a few files changed.

<AccordionGroup>
  <Accordion title="preview_delta_flash — Dry-run rsync">
    Runs `rsync --dry-run` to report exactly which files would be transferred.
    No changes are made to the device. Linux and macOS only.
  </Accordion>

  <Accordion title="apply_delta_flash — Apply incremental deploy">
    Executes the real rsync over SSH. Requires destructive confirmation.
    Optionally runs a post-command (e.g., `depmod`) and reboots the device.
    Linux and macOS only.
  </Accordion>
</AccordionGroup>

***

## Troubleshooting

<AccordionGroup>
  <Accordion title="MCP Server shows 'Stopped' in the sidebar">
    1. Open VS Code Settings and confirm `qvsce.mcpServer.enabled` is checked.
    2. Check that nothing else is using port 3100 (`lsof -i :3100` on Linux/macOS). If there is a conflict, change `qvsce.mcpServer.port` to a free port.
    3. Reload the VS Code window (`Ctrl+Shift+P` → **Developer: Reload Window**).
  </Accordion>

  <Accordion title="AI assistant cannot find any tools">
    Confirm the MCP client is configured to connect to `http://127.0.0.1:<port>/mcp` (not `/sse` or the root path). The server uses the **Streamable HTTP** transport, not the legacy SSE-only transport.
  </Accordion>

  <Accordion title="search_cpp_samples returns no results">
    The `qvsce.cppRag.samplesDir` setting may be empty or pointing to a directory with no `.cpp`/`.h` files. Set it to a valid path and call `build_cpp_rag_index` to populate the index.
  </Accordion>

  <Accordion title="Linux-only tools fail on WSL">
    Make sure you have opened VS Code connected to WSL (the status bar should show **WSL: Ubuntu** or similar) rather than using a Windows-native VS Code window with the extension installed on the Windows side.
  </Accordion>
</AccordionGroup>