de en es ja ko ru zh

Secure Agent MCP Gateway

Name: Secure Agent MCP Gateway
Author: aki83reo

by aki83reo

Overview Schema Related Servers Score Discussions

Python

Hybrid

Безопасный шлюз MCP для агента

Триаж оповещений SOC с защитным шлюзом MCP-to-MCP: агент никогда не взаимодействует с реальными инструментами напрямую. Каждый tools/list / tools/call ограничен и авторизован по роли (viewer | operator | admin).

main.py (agent)  →  gateway  →  mcp_server (tools)

Подробнее: gateway/README.md.

Быстрый старт (локально)

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)

Три ролевых сервиса (локально)

# 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.json

Детерминированный путь (без MCP / без шлюза):

python main.py --alert sample_alert.json

Проверка только по политике:

python -m gateway.policy

Related MCP server: Nervora

Развертывание в Docker

Требуется Docker + Compose. Секреты остаются вне образа:

cp .env.example .env
# set LLM_API_KEY in .env

Сборка

docker compose build
# or:
docker build -t secure-agent-mcp-gateway:latest .

Три сервиса (по одной роли каждый)

Один и тот же образ; разные GATEWAY_ROLE. Каждый контейнер запускает полную цепочку (main → gateway → mcp_server) для своей роли.

# 1) Viewer
docker compose run --rm triage-viewer

# 2) Operator
docker compose run --rm triage-operator

# 3) Admin
docker compose run --rm triage-admin

Или запустите по имени сервиса:

docker compose up triage-viewer
docker compose up triage-operator
docker compose up triage-admin

Передайте ключ без файла:

LLM_API_KEY=sk-... docker compose run --rm triage-admin

Обычный Docker (без Compose)

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.json

Переменные окружения

Переменная	Назначение
`LLM_API_KEY`	Требуется для агента / сводки результатов
`LLM_MODEL`	По умолчанию `gpt-4o-mini`
`LLM_PROVIDER`	По умолчанию `openai`
`GATEWAY_ROLE`	`viewer` \| `operator` \| `admin`

.env игнорируется git. Коммитится только .env.example.

Роли (политика)

Роль	Может использовать
`viewer`	`check_ip_reputation`
`operator`	репутация, триаж, сводка, уведомление
`admin`	все инструменты, включая `block_ip` + `escalate_alert`

Определено в gateway/policy.yaml.

This server cannot be installed

license - not found

Not graded

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

Enterprise MCP Gateway and
Agent Orchestration Security
Devarinti9
A
license
Not graded
quality
C
maintenance
Enables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.
Updated 2 months ago (2026-06-10 02:59 UTC)
1
MIT
Nervora
Security Agent Orchestration
sveselaj
A
license
Not graded
quality
C
maintenance
A secure MCP gateway for enterprise AI tool execution, enabling governed invocation of business tools with authentication, RBAC, audit logging, PII redaction, and async processing.
Updated 2 months ago (2026-06-30 06:17 UTC)
Apache 2.0
ToolBastion
Security Developer Tools
MaharMuavia
A
license
Not graded
quality
A
maintenance
A zero-trust security gateway for MCP tool calls, inspecting tool identity, arguments, execution decisions, and returned content before risk reaches your coding agent.
Updated a month ago (2026-07-21 16:34 UTC)
Apache 2.0
AgentsGateofficial
Agent Orchestration Security
agentsgate
A
license
Not graded
quality
A
maintenance
Enables AI agents to securely call MCP tools with risk scoring, checkpoints, rollback, and approval workflows.
Updated 13 days ago (2026-08-10 02:59 UTC)
134
MIT

View all related MCP servers

Related MCP Connectors

Oakallow
Runtime permission, approval, and audit layer for AI agent tool execution.
shadowgate-mcp
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
a2aidentitytoll-mcp
Remote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/aki83reo/secure-agent-mcp-gateway'

If you have feedback or need assistance with the MCP directory API, please join our Discord server