convez.ai
MCP ServerDevOps & InfraestruturaIntermediário
Knuckles-Team

Tunnel Manager

Knuckles-Team/tunnel-manager

Túneis SSH gerenciados como MCP Server para agentes de IA

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP Server em Python que cria e gerencia túneis SSH para hosts remotos, expondo-os como ferramentas para agentes de IA. Oferece interface CLI, API e integração nativa com o protocolo MCP, com suporte a segurança corporativa e telemetria.

Instalação

$npx convez-ai Knuckles-Team/tunnel-manager

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
0
Saúde
50%
Último commit
há 5 dias
Versão
v3.5.2
Issues abertas
0
Contribuidores
3

Casos de uso

  • Conectar agentes de IA a servidores remotos via SSH
  • Automatizar gerenciamento de inventário de hosts
  • Expor operações de tunelamento para aplicações agentic

Veredito

Ferramenta sólida para cenários onde agentes de IA precisam acessar infraestrutura remota via SSH. Bem mantida e com recursos enterprise, mas direcionada a casos de uso específicos de automação e operações.

README

A tradução para o português deste README ainda está na fila.

Tunnel Manager

CLI or API | MCP | Agent

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 1.31.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP and agent interfaces are maintained in the official documentation.


Overview

Tunnel Manager is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Create SSH Tunnels to your remote hosts and host as an MCP Server for Agentic AI!.


Key Features

  • Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
  • Enterprise-Grade Security: Comprehensive support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
  • Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
  • Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

CLI or API

This agent wraps the Create SSH Tunnels to your remote hosts and host as an MCP Server for Agentic AI! API. You can interact with it programmatically or via its integrated execution entrypoints.

Detailed instructions on how to use the underlying API wrappers, extended schema bindings, and developer SDK references are maintained in docs/index.md.


MCP

This server utilizes dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool ModuleToggle Env VarEnabled by DefaultDescription & Nested Methods
HostHOST_TOOLTrueRegister host inventory management tool. Action-routed methods: add, list, remove.
RemoteREMOTE_TOOLTrueRegister single-host SSH operations tool. Action-routed methods: check_ssh, copy_ssh_config, receive_file, remove_host_key, rotate_key, run_command, send_file, setup_passwordless, test_key_auth.
InventoryINVENTORY_TOOLTrueRegister bulk inventory operations tool. Action-routed methods: configure_key_auth, copy_ssh_config, mesh_bootstrap, receive_file, rotate_key, run_command, send_file.
OperationsOPERATIONS_TOOLTrueRegister operation lifecycle and session management tool. Action-routed methods: cancel, get_metrics, get_progress, list_sessions, start.
SystemSYSTEM_TOOLTrueRegister remote system intelligence tool. Action-routed methods: analyze_logs, discover_services, get_info, network_topology.
FileFILE_TOOLTrueRegister advanced file operations tool. Action-routed methods: backup, content_search, diff_compare, recursive_ops, watch.
SecuritySECURITY_TOOLTrueRegister security scanning and compliance tool. Action-routed methods: access_control_audit, compliance_check, security_audit, vulnerability_scan.

Detailed tool schemas, parameter shapes, and validation constraints are preserved in docs/mcp.md.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows you to restrict the set of exposed tools in order to prevent blowing up the LLM's context window.

You can configure tool filtering via multiple input channels:

  • CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
  • Environment Variables: Define standard environment variables:
    • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
    • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
  • HTTP SSE Request Headers: Pass custom headers during transport initialization:
    • x-mcp-enabled-tools / x-mcp-disabled-tools
    • x-mcp-enabled-tags / x-mcp-disabled-tags
  • HTTP SSE Request Query Parameters: Append query parameters directly to your transport connection URL:
    • ?tools=tool1,tool2
    • ?tags=tag1

When query strings or parameters are supplied, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.


MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

Configure your IDE's mcp.json to launch the MCP server via uvx:

{
  "mcpServers": {
    "tunnel-manager": {
      "command": "uvx",
      "args": [
        "--from",
        "tunnel-manager",
        "tunnel-manager-mcp"
      ],
      "env": {
        "TUNNEL_IDENTITY_FILE": "your_tunnel_identity_file_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

Configure your client's mcp.json to launch the Streamable-HTTP server via uvx with explicit host and port definition:

{
  "mcpServers": {
    "tunnel-manager": {
      "command": "uvx",
      "args": [
        "--from",
        "tunnel-manager",
        "tunnel-manager-mcp"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "TUNNEL_IDENTITY_FILE": "your_tunnel_identity_file_here",
        "DEBUG": "your_debug_here",
        "PYTHONUNBUFFERED": "your_pythonunbuffered_here"
      }
    }
  }
}

Alternatively, connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "tunnel-manager": {
      "url": "http://localhost:8000/tunnel-manager/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name tunnel-manager-mcp \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  -e TUNNEL_IDENTITY_FILE="your_value" \
  -e DEBUG="your_value" \
  -e PYTHONUNBUFFERED="your_value" \
  knucklessg1/tunnel-manager:latest

Additional Deployment Options

tunnel-manager can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

  • Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
  • Remote URL — connect to a server deployed behind Caddy at http://tunnel-manager-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts seamlessly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export TUNNEL_IDENTITY_FILE="your_value"
export DEBUG="your_value"
export PYTHONUNBUFFERED="your_value"

# Run the agent server
tunnel-manager-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The following docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface together:

version: '3.8'

services:
  tunnel-manager-mcp:
    image: knucklessg1/tunnel-manager:latest
    container_name: tunnel-manager-mcp
    hostname: tunnel-manager-mcp
    restart: always
    env_file:
      - ../.env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

  tunnel-manager-agent:
    image: knucklessg1/tunnel-manager:latest
    container_name: tunnel-manager-agent
    hostname: tunnel-manager-agent
    restart: always
    depends_on:
      - tunnel-manager-mcp
    env_file:
      - ../.env
    command: [ "tunnel-manager-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9002
      - MCP_URL=http://tunnel-manager-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9002:9002"
    healthcheck:
      test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:9002/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"

Detailed graph node architecture explanations, custom skill configurations, and agentic trace guides are available in docs/agent.md.


Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

  • Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
  • OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
  • Scoped Credentials: Execution context runs restricted to the specific caller identity.

Runtime Security Grid

FeatureFunctionalityEnablement
Tool GuardSensitivity inspection with human-in-the-loop validationEnabled by default
Prompt Injection DefenseInput scanning, repetition monitoring, and recursive loop blocksEnabled by default
Context Safety GuardStuck-loop detectors and contextual overflow preemptive alertsEnabled by default

Installation

Install the Python package locally:

# Using uv (highly recommended)
uv pip install tunnel-manager[all]

# Using standard pip
python -m pip install tunnel-manager[all]

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

PageContents
Installationpip, source, extras, prebuilt Docker image
Deploymentrun the MCP and agent servers, Compose, Caddy + Technitium, env config
Usagethe MCP tools, the HostManager / Tunnel API, the CLI
Overviewecosystem role, distributed SSH swarm scaling, MCP configuration
Teleport Architecturecertificate, proxy and cross-OS connection model
Conceptsconcept registry (CONCEPT:TUN-*)

AGENTS.md is the canonical contributor/agent guidance.

Repository Owners

GitHub followers GitHub User's stars


Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

  • Format code using ruff format .
  • Lint code using ruff check .
  • Validate type-safety with mypy .
  • Execute test suites using pytest
Ver o original no GitHub

Bom para

Relacionados