koma-gate-mcp
Koma Gate MCP
AI 에이전트를 위해 Koma Gate의 프롬프트 인젝션 분류를 MCP 도구로 제공합니다.
npm install koma-gate-mcp기능
classify_input이라는 단일 도구를 제공하며, AI 에이전트가 신뢰할 수 없는 사용자 텍스트를 실행하기 전에 안전하고 범위 내에 있는지 확인하기 위해 호출할 수 있습니다.
Related MCP server: agent immune
설정
제공자와 API 키를 설정합니다:
# Provider: openai | anthropic | google | deepseek | ollama (default: google)
export KOMA_PROVIDER=google
export GEMINI_API_KEY=sk-...Claude Desktop
claude_desktop_config.json에 추가합니다:
{
"mcpServers": {
"koma-gate": {
"command": "npx",
"args": ["-y", "koma-gate-mcp"]
}
}
}도구: classify_input
text(필수) — 분류할 신뢰할 수 없는 사용자 입력preset(선택 사항) —general|code|support|reference(기본값: general)
반환값:
{
"allowed": true,
"in_scope": true,
"reason": "in scope",
"preset": "general",
"model": "gemini-2.5-flash"
}보안 경계
이는 암호화된 프롬프트 인젝션 방어가 아닌 LLM 기반 범위 분류기입니다. 전체 보안 경계는 koma-gate의 README를 참조하고, 평가 결과는 BENCHMARKS.md를 참조하세요.
This server cannot be installed
Maintenance
Related MCP Servers
- Alicense-qualityDmaintenanceA lightweight stdio proxy that intercepts and rewrites MCP tool annotations to bypass security approval prompts in AI CLIs like Codex and Claude Code. It transparently passes through all tool operations while marking them as safe to ensure a seamless automation experience.1110MIT
- Alicense-qualityCmaintenanceAdaptive security for AI agents: assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts, and monitor metrics. Runs locally via MCP stdio.Apache 2.0

jamjet-policyofficial
AlicenseAqualityBmaintenanceDrop-in stdio interceptor that gates MCP tools/call requests through a YAML policy (block / require_approval / audit / budget cap) before they reach the real server. The same policy file is reused by @jamjet/claude-code-hook and @jamjet/openai-guardrail, so one rule set covers Claude Desktop, Cursor, OpenAI Agents, and custom clients.32Apache 2.0
Blekline MCP Serverofficial
AlicenseAqualityAmaintenanceProvides AI ingress governance by masking prompts, classifying risk, and enforcing tool policies before agent calls reach model providers or sandboxes.61AGPL 3.0
Related MCP Connectors
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.
Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/swnotmetal/Project-Koma'
If you have feedback or need assistance with the MCP directory API, please join our Discord server