{
"mcpServers": {
"fusionbrain-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 226 days ago.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Fusionbrain Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
FusionBrain MCP Server is an MCP server application based on Java + Spring Boot and FusionBrain SDK Starter.
The server provides tools for generating images by using FusionBrain API.
application.yml, environment variables, or JVM options.startGenerateImage — starts image generation and returns task idcheckStatus — checks the status of started task by idgenerateImageSync — starts image generation and blocks until image is readyFusionBrain MCP Server uses default SDK settings, but they can be overridden. Some properties like api-key and secret-key are obligatory and must be defined.
| Property | Description | Default |
|--------------------------|--------------------------------|-------------------------------|
| fusionbrain.api-key | API key for FusionBrain access | — (required) |
| fusionbrain.api-secret | Secret key for FusionBrain access | — (required) |
| fusionbrain.base-url | FusionBrain server URL | https://api-key.fusionbrain.ai |
The full list of sdk properties can be found here.
This server is based on Spring AI MCP Server Boot Starter. Properties of Spring AI can be overridden if needed.
This MCP server can be run with stdio transport and SSE (default option).
stdio transport can be set by activating Spring profile stdio:
java -Dspring.profiles.active=stdio ... -jar fusionbrain-mcp-server.jar
Note that in stdio profile logging to console is disabled, and you have to activate file logs by defining:
logging.file.path=/app/logs # directory where rolling log files are collected
logging.file.name=/app/logs/mcp-server.log # path to a log file
Via JVM options:
java -jar \
-Dfusionbrain.api-key=<your-api-key> \
-Dfusionbrain.secret-key=<your-secret-key> \
fusionbrain-mcp-server.jar
Via environment variables:
export FUSIONBRAIN_APIKEY=<your-api-key>
export FUSIONBRAIN_SECRETKEY=<your-secret-key>
java -jar fusionbrain-mcp-server.jar
.jar from sourcecd <path/to/fusionbrain-mcp-server>
make build
The built file will be located at:
target/fusionbrain-mcp-server-<version>.jar
cd <path/to/fusionbrain-mcp-server>
make docker
The built image will be named:
fusionbrain-mcp-server:latest
java -jar \
-Dfusionbrain.api-key=your-api-key \
-Dfusionbrain.secret-key=your-secret-key \
target/FusionBrain-mcp-server.jar
docker run --rm \
-e FUSIONBRAIN_APIKEY=your-api-key \
-e FUSIONBRAIN_SECRETKEY=your-api-key \
-e JAVA_OPTS=<your jvm options> \
-p 8080:8080 \
fusionbrain-mcp-server:latest
startGenerateImageStart image generation. Accepts the following request format:
{
"request": {
"style": "",
"width": 1024,
"height": 1024,
"prompt": "your prompt"
}
}
By default, width and height values are 1024.
This tool accepts these generation params and calls image generation API.
As generation takes some time to be finished, this tool does not wait for it and returns taskId, by which the status of the generation can be requested.
R