Genio520 ISP MCP

An MCP development bridge for Genio 520: inspect and edit a local source workspace, build a Camera2 diagnostic APK, deploy it through ADB, and retrieve YUV images with capture metadata.

Uses standard Node.js and the official MCP TypeScript SDK. No code indexer, AI runtime, MediaTek BSP, or vendor SDK binary is included. Each user connects their own Android board to their own Windows PC.

Install

Install Node.js 22 or later, Git, JDK 21, and Android SDK platform-tools, platform 35 and build-tools 35.0.0. Android Studio's JBR can supply the JDK. Source-only tools can run without a board; camera build/deploy currently requires Windows.

git clone https://github.com/eric612/Genio520_ISP_MCP.git
cd Genio520_ISP_MCP
npm ci --ignore-scripts
node bin/genio-dev-mcp.mjs doctor

Set GENIO_ANDROID_SDK and GENIO_JDK for custom installations. With exactly one ADB device, no serial is needed; set GENIO_SERIAL for multiple devices. The doctor reports missing prerequisites; it does not install SDKs or flash firmware.

Related MCP server: flutter-bridge-mcp

Local MCP client

Copy examples/mcp.local.json, replace the workspace path, and configure your client to launch it. --write enables edits and commits; omit it for inspection and camera validation. Use an absolute Node executable path if the client's default is older than 22.

{
  "mcpServers": {
    "genio_dev": {
      "command": "node",
      "args": ["D:/dev/Genio520_ISP_MCP/bin/genio-dev-mcp.mjs", "--workspace", "D:/dev/Genio520_ISP_MCP", "--write"]
    }
  }
}

Ask the AI to list sources, read a file, edit it using the returned SHA256, inspect the diff, then build and validate. Edits are restricted to allowed source paths within the workspace. New files require existing parent directories. There is no general shell tool. Building modified source executes it with the local user's permissions; use a workspace and AI client you trust.

Browser AI

Installing the repository alone does not connect a browser AI to the PC. See browser connection instructions. A token-protected, loopback-only Streamable HTTP endpoint is available; it is not an OAuth implementation or a public shared service.

For ChatGPT, the documented private connection is Secure MCP Tunnel, which can forward to this stdio server. It requires the user's own tunnel/account permissions and runtime key. No shared credentials are included. Account-specific browser testing is separate from local MCP protocol testing.

Validate

See validated behavior and remaining scope.

npm test
node tools/mcp_smoke.mjs --run

The camera test closes the existing camera app, installs the diagnostic app, grants it CAMERA permission, wakes the board and captures YUV. The controls suite collects 3 frames for each of 7 cases: auto, two exposures, NR OFF/FAST and linear/lifted tone curves. Each case saves its first frame as NV21 and a viewing JPEG. Reports and the exact APK are stored in outputs/camera-runs/<run-id>/.

Control readback does not prove image quality, temporal NR implementation, hardware HDR, sustained frame rate, power or end-to-end latency. WDR/Defog/TNR implementations and other projects' data are not included.

The ISP inventory, RAW capture and NR-control suites inspect the control surface before integrating enhancement algorithms. On the tested Genio 520/Android 15 build, full-resolution RAW16/DNG with timestamp-matched YUV and independent standard NR/vendor 3DNR control readback passed. Internal ISP stage export and noise-reduction quality remain unverified.

Version 0.3.0 adds simple WB tuning, native JPEG capture, RAW development and live preview. WB uses bounded R/Ge/Go/B probes with fixed captured CCM/exposure, compares the same neutral ROI and returns to AUTO. A physically changed camera or scene needs a new baseline. Python RAW inspection and scrcpy preview are optional local tools; neither is required by the MCP server.

Version 0.4.0 adds static lowlight NR sequences, evaluation and optional Windows scheduling: 64 matched YUV samples per manual NR/3DNR case, fixed current-light exposure/color, and explicit drift/gap/return checks. The server exposes 13 tools. Offline tests and APK compilation pass; the new sequence's on-board behavior and lowlight quality remain pending hardware validation.

Version 0.4.1 adds an optional external algorithm replay harness for hash-pinned NV21 inputs, source/recipe snapshots, independent decoder checks and deterministic WDR/chroma reference outputs. It does not ship external algorithm code or claim Android algorithm execution or approved visual quality.

For repeated builds, keep the same local development keystore. When moving a source checkout, set GENIO_CAMERA_KEYSTORE to the original development.keystore (development alias/password as generated by this project's build script). Different signatures cannot update the same installed app. The tool reports that installation error; it does not uninstall the app or erase its captures. Never commit or distribute the keystore.

The standalone native ARM64 deployment probe is a saturating multiply-by-two fixture, not an ISP algorithm.

License

Public MCP source is MIT licensed. Dependency copyright and license texts are preserved in THIRD_PARTY_NOTICES.md. Android/JDK tools are installed separately under their own terms. No official board photographs, SDK binaries, camera captures or signing keys are distributed.