Gpt Image MCP vs Kokon
A side-by-side look at the Gpt Image MCP and Kokon MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
K
KokonMultimedia Process · Local subprocess (stdio)Generate and edit images offline with Qwen-Image 2.1 on your GPU. Needs the Kokon desktop app.49FairAuth: not declaredVerdict: choose Gpt Image MCP for multimedia process work as a local process; choose Kokon for multimedia process as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Gpt Image MCP when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
YOUBOT_API_KEY, YOUBOT_IMAGE_DIR. - You want tools like
generate_image, edit_image, check_credits.
KChoose Kokon when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | K Kokon | |
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 55/100 · Good | 49/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | YOUBOT_API_KEYYOUBOT_IMAGE_DIR | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 127 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 3 | Not listed |
| Full listing | View Gpt Image MCP | View Kokon |
Tools & capabilities
Gpt Image MCP tools 3
generate_imageMake an image from a text promptedit_imageChange an existing image from a public URL — swap a background, add or remove objects, restylecheck_creditsShow remaining balance and images left
Kokon tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Gpt Image MCP
{
"mcpServers": {
"gpt-image-mcp-2": {
"command": "npx",
"args": [
"-y",
"gpt-image-2-5-mcp"
],
"env": {
"YOUBOT_API_KEY": "YOUR_YOUBOT_API_KEY_HERE",
"YOUBOT_IMAGE_DIR": "YOUR_YOUBOT_IMAGE_DIR_HERE"
}
}
}
}
Kokon
{
"mcpServers": {
"kokon": {
"command": "npx",
"args": [
"-y",
"kokon-mcp"
]
}
}
}
Frequently asked questions
Gpt Image MCP is categorized under Multimedia Process and uses a local stdio subprocess. Kokon belongs to Multimedia Process and uses a local stdio subprocess. Pick Gpt Image MCP for multimedia process work and Kokon for multimedia process.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Gpt Image MCP has no declared pricing — check the project's own site. Kokon has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add gpt-image-mcp-2 and kokon as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Gpt Image MCP has a quality signal of 55/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Kokon has 49/100 (Fair) with 0 views, 0 installs and 127 GitHub stars.