Skip to main content
Glama
Sign In
deenesjakoruzh
Secure Agent MCP Gateway

Secure Agent MCP Gateway

by aki83reo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Secure Agent MCP Gateway

SOC-Alert-Triage mit einem MCP-zu-MCP-Sicherheitsgateway: Der Agent kommuniziert nie direkt mit echten Tools. Jeder tools/list- / tools/call-Aufruf wird anhand der Rolle (viewer | operator | admin) eingeschränkt und autorisiert.

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

Weitere Details: gateway/README.md.

Schnellstart (lokal)

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)

Drei Rollen-Dienste (lokal)

# 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

Deterministischer Pfad (ohne MCP / ohne Gateway):

python main.py --alert sample_alert.json

Reine Policy-Prüfung:

python -m gateway.policy

Related MCP server: production-mcp-server

Docker-Deployment

Erfordert Docker + Compose. Secrets bleiben außerhalb des Images:

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

Erstellen

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

Drei Dienste (je eine Rolle)

Dasselbe Image; unterschiedliche GATEWAY_ROLE. Jeder Container führt die vollständige Kette (main → gateway → mcp_server) für diese Rolle aus.

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

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

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

Oder nach Dienstnamen starten:

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

Den Schlüssel ohne Datei übergeben:

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

Reines Docker (ohne 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

Umgebung

Variable

Zweck

LLM_API_KEY

Erforderlich für Agent und Findings-Zusammenfassung

LLM_MODEL

Standard gpt-4o-mini

LLM_PROVIDER

Standard openai

GATEWAY_ROLE

viewer | operator | admin

.env ist gitignoriert. Nur .env.example wird committet.

Rollen (Policy)

Rolle

Kann verwenden

viewer

check_ip_reputation

operator

reputation, triage, summarize, notify

admin

alle Tools einschließlich block_ip + escalate_alert

Definiert in gateway/policy.yaml.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityStale
ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Related MCP Servers

  • Nervora

    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.
    Apache 2.0

  • production-mcp-server

    TushGoel
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables 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

  • MCP Security Gateway

    qylhjhd
    A
    license
    A
    quality
    C
    maintenance
    Provides 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.
    2
    1
    Apache 2.0