Koma Gate MCP
Classify input for prompt injection and out-of-scope content with Koma Gate's LLM-based classifier.
What can you do with Koma Gate MCP?
text(required) — the untrusted user input to classifypreset(optional) —general|code|support|reference(default: general)
Install
The installation steps are in the documentation below. Documentation
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Koma Gate MCP
Expose Koma Gate's prompt-injection classification as an MCP tool for AI agents.
npm install koma-gate-mcp
What it does
Provides a single tool, classify_input, that an AI agent can call to check whether untrusted user text is safe and in-scope before acting on it.
Setup
Set the provider and API key:
# Provider: openai | anthropic | google | deepseek | ollama (default: google)
export KOMA_PROVIDER=google
export GEMINI_API_KEY=sk-...
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"koma-gate": {
"command": "npx",
"args": ["-y", "koma-gate-mcp"]
}
}
}
Tool: classify_input
text(required) — the untrusted user input to classifypreset(optional) —general|code|support|reference(default: general)
Returns:
{
"allowed": true,
"in_scope": true,
"reason": "in scope",
"preset": "general",
"model": "gemini-2.5-flash"
}
Security Boundary
This is an LLM-based scope classifier, not a cryptographic prompt-injection defense. See koma-gate's README for the full security boundary and BENCHMARKS.md for evaluation results.
Frequently asked questions
What is Koma Gate MCP?
Classify input for prompt injection and out-of-scope content with Koma Gate's LLM-based classifier.
How do I install Koma Gate MCP?
Follow the installation steps in its documentation, shown on this page and in its repository.
Is Koma Gate MCP open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains Koma Gate MCP?
It is published by swnotmetal. AI.tn lists it but does not maintain or endorse it.
From the community awesome-mcp-servers lists and the project's GitHub repository. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.