Secure Agent MCP Gateway
Secure Agent MCP Gateway
SOC 알림 트라이지(MCP-to-MCP 보안 게이트웨이)를 위한 보안 게이트웨이: 에이전트는 실제 도구와 직접 통신하지 않습니다. 모든 tools/list / tools/call은 역할(viewer | operator | admin)에 따라 범위가 지정되고 권한이 부여됩니다.
main.py (agent) → gateway → mcp_server (tools)자세한 내용: gateway/README.md
빠른 시작(로컬)
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# edit .env — set LLM_API_KEY (never commit .env)세 가지 역할 서비스(로컬)
# 1) Viewer — reputation lookups only
python main.py --mcp --role viewer --alert sample_alert.json
# 2) Operator — triage / summarize / notify (no block or escalate)
python main.py --mcp --role operator --alert sample_alert.json
# 3) Admin — full tool set through the gateway
python main.py --mcp --role admin --alert sample_alert.json결정적 경로(MCP / 게이트웨이 없음):
python main.py --alert sample_alert.json정책 전용 확인:
python -m gateway.policyRelated MCP server: production-mcp-server
Docker 배포
Docker + Compose 필요. 비밀번호는 이미지 외부에 유지됩니다:
cp .env.example .env
# set LLM_API_KEY in .env빌드
docker compose build
# or:
docker build -t secure-agent-mcp-gateway:latest .세 가지 서비스(각각 하나의 역할)
동일한 이미지; 다른 GATEWAY_ROLE. 각 컨테이너는 해당 역할에 대한 전체 체인(main → gateway → mcp_server)을 실행합니다.
# 1) Viewer
docker compose run --rm triage-viewer
# 2) Operator
docker compose run --rm triage-operator
# 3) Admin
docker compose run --rm triage-admin또는 서비스 이름으로 시작:
docker compose up triage-viewer
docker compose up triage-operator
docker compose up triage-admin파일 없이 키 전달:
LLM_API_KEY=sk-... docker compose run --rm triage-admin일반 Docker(Compose 없음)
docker build -t secure-agent-mcp-gateway:latest .
docker run --rm \
-e LLM_API_KEY \
-e LLM_MODEL=gpt-4o-mini \
-e GATEWAY_ROLE=viewer \
secure-agent-mcp-gateway:latest \
python main.py --mcp --role viewer --alert sample_alert.json
docker run --rm -e LLM_API_KEY -e GATEWAY_ROLE=operator \
secure-agent-mcp-gateway:latest \
python main.py --mcp --role operator --alert sample_alert.json
docker run --rm -e LLM_API_KEY -e GATEWAY_ROLE=admin \
secure-agent-mcp-gateway:latest \
python main.py --mcp --role admin --alert sample_alert.json환경
변수 | 용도 |
| 에이전트 / 결과 요약에 필요 |
| 기본값 |
| 기본값 |
|
|
.env는 gitignore 처리됩니다. .env.example만 커밋됩니다.
역할(정책)
역할 | 사용 가능 |
|
|
| 평판, 트라이프, 요약, 알림 |
|
|
gateway/policy.yaml에 정의되어 있습니다.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
MCP gateway: one connection for your AI apps, with tool policies, PII redaction and audit logs.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA secure MCP gateway for enterprise AI tool execution, enabling governed invocation of business tools with authentication, RBAC, audit logging, PII redaction, and async processing.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to safely call enterprise tools through a governed MCP gateway with permission enforcement, blast-radius controls, input validation, and a full audit trail for every invocation.MIT
- AlicenseAqualityCmaintenanceProvides a security governance layer for AI agents to safely access upstream MCP servers, enforcing tool-level RBAC, parameter constraints, authentication via static tokens or OIDC, and tamper-evident audit logging.21Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables governed MCP agent tool invocation with policy-based authorization, short-lived credentials, and audited access control.11 npmMIT