visiongemma-mcp 2.1.0__tar.gz

visiongemma_mcp-2.1.0/PKG-INFO

@@ -0,0 +1,81 @@
+Metadata-Version: 2.4
+Name: visiongemma-mcp
+Version: 2.1.0
+Summary: Local AI vision MCP server for Windows: OCR (Chinese & English), chart analysis, scene description, object recognition. 100% offline — images never leave your machine.
+Author: q1023884985
+License: Proprietary
+Keywords: mcp,vision,ocr,llm,computer-vision,local
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Win32 (MS Windows)
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# VisionGemma MCP
+
+mcp-name: io.github.q1023884985/visiongemma
+
+**VisionGemma** is a local AI vision recognition MCP server for Windows. It exposes a single `vision_analyze` tool that lets any MCP client (Claude Desktop, Cursor, Cline, opencode, ...) do:
+
+- **OCR** — extract text from images and screenshots (Chinese & English)
+- **Chart / diagram analysis** — interpret tables, plots, diagrams and screenshots
+- **Scene description** — describe what is in an image
+- **Object recognition** — identify objects, people, expressions, atmosphere
+
+All inference runs **100% locally** via a Vulkan-accelerated on-device engine. Images never leave your machine.
+
+> **Note:** this package is the stdio launcher for the MCP Registry. It requires the VisionGemma engine (Windows x64) to be installed. Download it from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases), then run the installer once.
+
+## Installation
+
+```
+pip install visiongemma-mcp
+```
+
+Install the VisionGemma engine from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases) page.
+
+## MCP configuration
+
+Add to your MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "visiongemma",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+Or point directly at the engine executable (no pip install needed):
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "C:\\path\\to\\VisionGemma.exe",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+## Tool: vision_analyze
+
+| Parameter | Type | Description |
+|---|---|---|
+| `image_path` | string (required) | Local absolute path, `http(s)://` URL, or base64 data URI of the image |
+| `prompt` | string (optional) | Question or instruction about the image (default: "please describe this image") |
+
+## Privacy & licensing
+
+- All processing is local and offline — no data leaves your device.
+- Free 7-day trial; 38 CNY one-time purchase to keep it forever. See in-app activation.
+- Windows 10/11 x64, Vulkan-capable GPU (or CPU fallback).

visiongemma_mcp-2.1.0/README.md

@@ -0,0 +1,65 @@
+# VisionGemma MCP
+
+mcp-name: io.github.q1023884985/visiongemma
+
+**VisionGemma** is a local AI vision recognition MCP server for Windows. It exposes a single `vision_analyze` tool that lets any MCP client (Claude Desktop, Cursor, Cline, opencode, ...) do:
+
+- **OCR** — extract text from images and screenshots (Chinese & English)
+- **Chart / diagram analysis** — interpret tables, plots, diagrams and screenshots
+- **Scene description** — describe what is in an image
+- **Object recognition** — identify objects, people, expressions, atmosphere
+
+All inference runs **100% locally** via a Vulkan-accelerated on-device engine. Images never leave your machine.
+
+> **Note:** this package is the stdio launcher for the MCP Registry. It requires the VisionGemma engine (Windows x64) to be installed. Download it from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases), then run the installer once.
+
+## Installation
+
+```
+pip install visiongemma-mcp
+```
+
+Install the VisionGemma engine from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases) page.
+
+## MCP configuration
+
+Add to your MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "visiongemma",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+Or point directly at the engine executable (no pip install needed):
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "C:\\path\\to\\VisionGemma.exe",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+## Tool: vision_analyze
+
+| Parameter | Type | Description |
+|---|---|---|
+| `image_path` | string (required) | Local absolute path, `http(s)://` URL, or base64 data URI of the image |
+| `prompt` | string (optional) | Question or instruction about the image (default: "please describe this image") |
+
+## Privacy & licensing
+
+- All processing is local and offline — no data leaves your device.
+- Free 7-day trial; 38 CNY one-time purchase to keep it forever. See in-app activation.
+- Windows 10/11 x64, Vulkan-capable GPU (or CPU fallback).

visiongemma_mcp-2.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "visiongemma-mcp"
+version = "2.1.0"
+description = "Local AI vision MCP server for Windows: OCR (Chinese & English), chart analysis, scene description, object recognition. 100% offline — images never leave your machine."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Proprietary" }
+authors = [{ name = "q1023884985" }]
+keywords = ["mcp", "vision", "ocr", "llm", "computer-vision", "local"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Environment :: Win32 (MS Windows)",
+    "Intended Audience :: Developers",
+    "Operating System :: Microsoft :: Windows",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = []
+
+[project.scripts]
+visiongemma = "visiongemma_mcp:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["visiongemma_mcp*"]

visiongemma_mcp-2.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

visiongemma_mcp-2.1.0/src/visiongemma_mcp/__init__.py

@@ -0,0 +1,4 @@
+from .launcher import main
+
+__all__ = ["main"]
+__version__ = "2.1.0"

visiongemma_mcp-2.1.0/src/visiongemma_mcp/__main__.py

@@ -0,0 +1,6 @@
+import sys
+
+from .launcher import main
+
+if __name__ == "__main__":
+    sys.exit(main())

visiongemma_mcp-2.1.0/src/visiongemma_mcp/launcher.py

@@ -0,0 +1,69 @@
+import os
+import shutil
+import subprocess
+import sys
+
+
+def _find_engine() -> str | None:
+    candidates = []
+
+    env = os.environ.get("VISIONGEMMA_EXE")
+    if env:
+        candidates.append(env)
+
+    local = os.path.join(os.environ.get("LOCALAPPDATA", ""), "VisionGemma", "VisionGemma.exe")
+    candidates.append(local)
+
+    prog = os.path.join(os.environ.get("PROGRAMFILES", ""), "VisionGemma", "VisionGemma.exe")
+    candidates.append(prog)
+
+    in_path = shutil.which("VisionGemma.exe")
+    if in_path:
+        candidates.append(in_path)
+
+    for c in candidates:
+        if c and os.path.isfile(c):
+            return c
+    return None
+
+
+def main() -> int:
+    exe = _find_engine()
+    if exe is None:
+        sys.stderr.write(
+            "VisionGemma engine not found.\n"
+            "Download and install it from https://github.com/q1023884985/visiongemma/releases\n"
+            "or set the VISIONGEMMA_EXE environment variable to the VisionGemma.exe path.\n"
+        )
+        return 1
+
+    proc = subprocess.Popen(
+        [exe, "--mcp"],
+        stdin=subprocess.PIPE,
+        stdout=subprocess.PIPE,
+        stderr=sys.stderr,
+    )
+
+    def pump(src, dst):
+        try:
+            while True:
+                chunk = src.read(4096)
+                if not chunk:
+                    break
+                dst.write(chunk)
+                dst.flush()
+        except Exception:
+            pass
+
+    import threading
+
+    t1 = threading.Thread(target=pump, args=(sys.stdin.buffer, proc.stdin), daemon=True)
+    t2 = threading.Thread(target=pump, args=(proc.stdout, sys.stdout.buffer), daemon=True)
+    t1.start()
+    t2.start()
+    proc.wait()
+    return proc.returncode
+
+
+if __name__ == "__main__":
+    sys.exit(main())

visiongemma_mcp-2.1.0/src/visiongemma_mcp.egg-info/PKG-INFO

@@ -0,0 +1,81 @@
+Metadata-Version: 2.4
+Name: visiongemma-mcp
+Version: 2.1.0
+Summary: Local AI vision MCP server for Windows: OCR (Chinese & English), chart analysis, scene description, object recognition. 100% offline — images never leave your machine.
+Author: q1023884985
+License: Proprietary
+Keywords: mcp,vision,ocr,llm,computer-vision,local
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Win32 (MS Windows)
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+
+# VisionGemma MCP
+
+mcp-name: io.github.q1023884985/visiongemma
+
+**VisionGemma** is a local AI vision recognition MCP server for Windows. It exposes a single `vision_analyze` tool that lets any MCP client (Claude Desktop, Cursor, Cline, opencode, ...) do:
+
+- **OCR** — extract text from images and screenshots (Chinese & English)
+- **Chart / diagram analysis** — interpret tables, plots, diagrams and screenshots
+- **Scene description** — describe what is in an image
+- **Object recognition** — identify objects, people, expressions, atmosphere
+
+All inference runs **100% locally** via a Vulkan-accelerated on-device engine. Images never leave your machine.
+
+> **Note:** this package is the stdio launcher for the MCP Registry. It requires the VisionGemma engine (Windows x64) to be installed. Download it from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases), then run the installer once.
+
+## Installation
+
+```
+pip install visiongemma-mcp
+```
+
+Install the VisionGemma engine from the [GitHub Releases](https://github.com/q1023884985/visiongemma/releases) page.
+
+## MCP configuration
+
+Add to your MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "visiongemma",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+Or point directly at the engine executable (no pip install needed):
+
+```json
+{
+  "mcpServers": {
+    "vision-gemma": {
+      "command": "C:\\path\\to\\VisionGemma.exe",
+      "args": ["--mcp"],
+      "type": "stdio"
+    }
+  }
+}
+```
+
+## Tool: vision_analyze
+
+| Parameter | Type | Description |
+|---|---|---|
+| `image_path` | string (required) | Local absolute path, `http(s)://` URL, or base64 data URI of the image |
+| `prompt` | string (optional) | Question or instruction about the image (default: "please describe this image") |
+
+## Privacy & licensing
+
+- All processing is local and offline — no data leaves your device.
+- Free 7-day trial; 38 CNY one-time purchase to keep it forever. See in-app activation.
+- Windows 10/11 x64, Vulkan-capable GPU (or CPU fallback).

visiongemma_mcp-2.1.0/src/visiongemma_mcp.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+src/visiongemma_mcp/__init__.py
+src/visiongemma_mcp/__main__.py
+src/visiongemma_mcp/launcher.py
+src/visiongemma_mcp.egg-info/PKG-INFO
+src/visiongemma_mcp.egg-info/SOURCES.txt
+src/visiongemma_mcp.egg-info/dependency_links.txt
+src/visiongemma_mcp.egg-info/entry_points.txt
+src/visiongemma_mcp.egg-info/top_level.txt

visiongemma_mcp-2.1.0/src/visiongemma_mcp.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

visiongemma_mcp-2.1.0/src/visiongemma_mcp.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+visiongemma = visiongemma_mcp:main

visiongemma_mcp-2.1.0/src/visiongemma_mcp.egg-info/top_level.txt

@@ -0,0 +1 @@
+visiongemma_mcp