@apresai/gimage-mcp 1.2.61 → 1.2.63
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/package.json +1 -1
- package/README.md +0 -186
package/package.json
CHANGED
package/README.md
DELETED
|
@@ -1,186 +0,0 @@
|
|
|
1
|
-
# @apresai/gimage-mcp
|
|
2
|
-
|
|
3
|
-
MCP (Model Context Protocol) server for AI-powered image generation and processing with gimage.
|
|
4
|
-
|
|
5
|
-
## Quick Start
|
|
6
|
-
|
|
7
|
-
### Installation
|
|
8
|
-
|
|
9
|
-
```bash
|
|
10
|
-
npm install -g @apresai/gimage-mcp
|
|
11
|
-
```
|
|
12
|
-
|
|
13
|
-
Or use without installation:
|
|
14
|
-
|
|
15
|
-
```bash
|
|
16
|
-
npx @apresai/gimage-mcp
|
|
17
|
-
```
|
|
18
|
-
|
|
19
|
-
### Configure Claude Desktop
|
|
20
|
-
|
|
21
|
-
Add to your Claude Desktop MCP configuration file:
|
|
22
|
-
|
|
23
|
-
**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
|
|
24
|
-
**Linux**: `~/.config/Claude/claude_desktop_config.json`
|
|
25
|
-
**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
|
|
26
|
-
|
|
27
|
-
```json
|
|
28
|
-
{
|
|
29
|
-
"mcpServers": {
|
|
30
|
-
"gimage": {
|
|
31
|
-
"command": "npx",
|
|
32
|
-
"args": ["-y", "@apresai/gimage-mcp"]
|
|
33
|
-
}
|
|
34
|
-
}
|
|
35
|
-
}
|
|
36
|
-
```
|
|
37
|
-
|
|
38
|
-
### Setup Authentication
|
|
39
|
-
|
|
40
|
-
Before using, configure your Gemini API key:
|
|
41
|
-
|
|
42
|
-
```bash
|
|
43
|
-
gimage auth gemini
|
|
44
|
-
```
|
|
45
|
-
|
|
46
|
-
Get your free API key from: https://aistudio.google.com/app/apikey
|
|
47
|
-
|
|
48
|
-
### Restart Claude Desktop
|
|
49
|
-
|
|
50
|
-
Quit and reopen Claude Desktop to load the MCP server.
|
|
51
|
-
|
|
52
|
-
## Features
|
|
53
|
-
|
|
54
|
-
The MCP server provides 10 tools for AI assistants:
|
|
55
|
-
|
|
56
|
-
### Image Generation
|
|
57
|
-
- **generate_image** - Create AI images from text prompts
|
|
58
|
-
- Multiple models: Gemini 2.5 Flash, Imagen 3, Imagen 4
|
|
59
|
-
- Sizes up to 2048x2048
|
|
60
|
-
- Style controls (photorealistic, artistic, anime)
|
|
61
|
-
- Negative prompts
|
|
62
|
-
- Reproducible generation with seeds
|
|
63
|
-
|
|
64
|
-
### Image Processing
|
|
65
|
-
- **resize_image** - Resize to specific dimensions
|
|
66
|
-
- **scale_image** - Scale by factor (maintain aspect ratio)
|
|
67
|
-
- **crop_image** - Crop to specific region
|
|
68
|
-
- **compress_image** - Reduce file size with quality control
|
|
69
|
-
- **convert_image** - Convert between formats (PNG, JPG, WebP, GIF, TIFF, BMP)
|
|
70
|
-
|
|
71
|
-
### Batch Operations
|
|
72
|
-
- **batch_resize** - Resize multiple images concurrently
|
|
73
|
-
- **batch_compress** - Compress multiple images
|
|
74
|
-
- **batch_convert** - Convert multiple images to new format
|
|
75
|
-
|
|
76
|
-
### Utilities
|
|
77
|
-
- **list_models** - List available AI models with details
|
|
78
|
-
|
|
79
|
-
## Usage Examples
|
|
80
|
-
|
|
81
|
-
Once installed and configured, you can use natural language in Claude:
|
|
82
|
-
|
|
83
|
-
**Image Generation**:
|
|
84
|
-
- "Generate an image of a sunset over mountains"
|
|
85
|
-
- "Create a photorealistic portrait of a wise old wizard"
|
|
86
|
-
- "Generate an anime-style image of cherry blossoms"
|
|
87
|
-
|
|
88
|
-
**Image Processing**:
|
|
89
|
-
- "Resize photo.jpg to 800x600"
|
|
90
|
-
- "Compress all images in the photos directory to 85% quality"
|
|
91
|
-
- "Convert image.png to WebP format"
|
|
92
|
-
|
|
93
|
-
**Batch Operations**:
|
|
94
|
-
- "Resize all images in the vacation-photos folder to 1920x1080"
|
|
95
|
-
- "Compress all PNG files to reduce storage space"
|
|
96
|
-
- "Convert all photos to WebP for web use"
|
|
97
|
-
|
|
98
|
-
## Requirements
|
|
99
|
-
|
|
100
|
-
- Node.js 18.0.0 or higher
|
|
101
|
-
- Gemini API key (free tier available) or Vertex AI access
|
|
102
|
-
|
|
103
|
-
## Supported Platforms
|
|
104
|
-
|
|
105
|
-
- macOS (Intel & Apple Silicon)
|
|
106
|
-
- Linux (x86_64 & ARM64)
|
|
107
|
-
- Windows (x86_64)
|
|
108
|
-
|
|
109
|
-
## Environment Variables
|
|
110
|
-
|
|
111
|
-
The server respects these environment variables:
|
|
112
|
-
|
|
113
|
-
- `GEMINI_API_KEY` - Gemini API key for image generation
|
|
114
|
-
- `VERTEX_API_KEY` - Vertex AI API key (Express Mode)
|
|
115
|
-
- `VERTEX_PROJECT` - GCP project ID for Vertex AI
|
|
116
|
-
- `VERTEX_LOCATION` - Vertex AI location (default: us-central1)
|
|
117
|
-
- `GOOGLE_APPLICATION_CREDENTIALS` - Path to service account JSON
|
|
118
|
-
|
|
119
|
-
## Troubleshooting
|
|
120
|
-
|
|
121
|
-
### Server not connecting
|
|
122
|
-
|
|
123
|
-
1. Verify gimage is installed:
|
|
124
|
-
```bash
|
|
125
|
-
which gimage
|
|
126
|
-
```
|
|
127
|
-
|
|
128
|
-
2. Test manually:
|
|
129
|
-
```bash
|
|
130
|
-
gimage serve
|
|
131
|
-
```
|
|
132
|
-
|
|
133
|
-
3. Check Claude Desktop logs
|
|
134
|
-
|
|
135
|
-
### Image generation fails
|
|
136
|
-
|
|
137
|
-
1. Verify API key is configured:
|
|
138
|
-
```bash
|
|
139
|
-
gimage auth gemini
|
|
140
|
-
```
|
|
141
|
-
|
|
142
|
-
2. Test generation manually:
|
|
143
|
-
```bash
|
|
144
|
-
gimage generate "test image"
|
|
145
|
-
```
|
|
146
|
-
|
|
147
|
-
## Alternative Installation Methods
|
|
148
|
-
|
|
149
|
-
### Homebrew (macOS/Linux)
|
|
150
|
-
|
|
151
|
-
```bash
|
|
152
|
-
brew install apresai/tap/gimage
|
|
153
|
-
```
|
|
154
|
-
|
|
155
|
-
Then configure Claude Desktop with:
|
|
156
|
-
|
|
157
|
-
```json
|
|
158
|
-
{
|
|
159
|
-
"mcpServers": {
|
|
160
|
-
"gimage": {
|
|
161
|
-
"command": "gimage",
|
|
162
|
-
"args": ["serve"]
|
|
163
|
-
}
|
|
164
|
-
}
|
|
165
|
-
}
|
|
166
|
-
```
|
|
167
|
-
|
|
168
|
-
### Manual Binary Download
|
|
169
|
-
|
|
170
|
-
Download from: https://github.com/apresai/gimage/releases
|
|
171
|
-
|
|
172
|
-
## Documentation
|
|
173
|
-
|
|
174
|
-
- [Complete MCP Tools Reference](https://github.com/apresai/gimage/blob/main/docs/MCP_TOOLS.md)
|
|
175
|
-
- [Usage Guide](https://github.com/apresai/gimage/blob/main/docs/MCP_USAGE.md)
|
|
176
|
-
- [Examples](https://github.com/apresai/gimage/blob/main/docs/MCP_EXAMPLES.md)
|
|
177
|
-
- [Main Documentation](https://github.com/apresai/gimage)
|
|
178
|
-
|
|
179
|
-
## License
|
|
180
|
-
|
|
181
|
-
MIT
|
|
182
|
-
|
|
183
|
-
## Support
|
|
184
|
-
|
|
185
|
-
- GitHub Issues: https://github.com/apresai/gimage/issues
|
|
186
|
-
- Documentation: https://github.com/apresai/gimage#readme
|