Skip to main content
Glama

Veeam Ports MCP Server

An MCP (Model Context Protocol) server that gives Claude structured access to Veeam product network port requirements. Query ports, generate topology diagrams, and produce firewall rule import files — all from natural language.

Backed by the Magic Ports API, covering 25+ Veeam products.

Installation

Claude Desktop

Add to your Claude Desktop config:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "veeam-ports": {
      "command": "uvx",
      "args": ["veeam-ports-mcp"]
    }
  }
}

Requires uv — a single binary install. uvx downloads and runs the package automatically with no repo clone needed.

VS Code / Claude Code

claude mcp add veeam-ports -- uvx veeam-ports-mcp

Development Install

git clone https://github.com/shapedthought/veeam-ports-mcp.git
cd veeam-ports-mcp
uv sync

Claude Desktop config for a local dev install:

{
  "mcpServers": {
    "veeam-ports": {
      "command": "uv",
      "args": [
        "run",
        "--directory", "/path/to/veeam-ports-mcp",
        "veeam-ports-mcp"
      ]
    }
  }
}

Related MCP server: Veeam Intelligence MCP Server

Available Tools

Tool

Description

list_products

List all Veeam products with port data

list_services

List available service roles for a product — call this before generate_topology or generate_app_import

get_product_ports

Get all port requirements for a product

get_product_subheadings

Get section headings for a product — use to find valid exclude_subsections values

search_ports

Free-text keyword search across all products

search_by_port_number

Find which products and services use a specific port

get_source_details

Source services with their section groupings

get_enriched_ports

Port data with LLM-parsed service metadata

generate_topology

Resolve firewall rules between named servers in your environment

generate_app_import

Generate a JSON import file for the Magic Ports frontend app

Topology & Import File Workflow

  1. Call list_services to see available service roles for the product

  2. Ask the user which servers they have and what roles each one serves

  3. Call generate_topology or generate_app_import with the server definitions

  4. Optionally exclude subsections (e.g. CDP Components) or specific ports with exclude_subsections / exclude_ports

User: "Generate firewall rules for my VBR v13 environment.
       I have a VBR server, two Linux proxies, a repo, and ESXi hosts behind vCenter."

Claude: [calls list_services → generate_app_import]
        "Import file saved: ~/Documents/veeam-ports-exports/magic-ports-vbr-v13-import.json"

Generated files are saved to ~/Documents/veeam-ports-exports/ by default.

Example Prompts

  • "What ports does VBR v13 need?"

  • "Which products use port 902 and why?"

  • "Show me all ports the backup server uses to talk to ESXi hosts"

  • "Generate firewall rules for my VBR environment — I have a VBR server, a Linux proxy, a repo server, and ESXi hosts managed by vCenter"

  • "Create a Magic Ports import file for my VB365 deployment, excluding the proxy ports"

  • "What ports does the Veeam ONE server need open?"

Configuration

Environment Variable

Default

Description

VEEAM_PORTS_API_BASE

https://magicports.veeambp.com/ports_server

API base URL

VEEAM_PORTS_OUTPUT_DIR

~/Documents/veeam-ports-exports

Directory for generated import files

Debugging

Use the MCP Inspector to test tools interactively:

npx @modelcontextprotocol/inspector uvx veeam-ports-mcp

License

MIT

Available Tools

11 tools
generate_app_importA

Generate a JSON file for importing into the Magic Ports frontend app.

Resolves the port mapping topology between user-defined servers using the enriched knowledge graph on the API server. The full JSON is written to a file on disk and a compact summary is returned.

Workflow:

  1. Call list_services to see available service roles for the product.

  2. Ask the user which servers they have and what roles they serve.

  3. Call this tool with the server definitions.

  4. Present the generated file to the user for download/import.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365') servers_json: JSON array of server definitions. Each object must have 'name' (server label) and 'services' (list of service names this server provides). Example: [ {"name": "VBR", "services": ["Backup server"]}, {"name": "Proxy", "services": ["Backup proxy"]}, {"name": "Repo", "services": ["Backup repository"]}, {"name": "ESXi", "services": ["ESXi host", "vCenter Server"]} ] output_dir: Optional directory to write the file to. Defaults to ~/Documents/veeam-ports-exports or VEEAM_PORTS_OUTPUT_DIR env var. exclude_subsections: Subsection names to exclude from results (e.g. ["CDP Components"]). Accepts a list or JSON string. exclude_ports: Port numbers to exclude from results (e.g. ["33035"]). Accepts a list or JSON string. format: Output format — 'json' (default), 'csv', or 'markdown'. csv and markdown return the raw content as text (no file written).

Inputs: product_name (required), servers_json (required), output_dir, exclude_subsections, +2 more. Returns: result

generate_topologyA

Resolve server topology — given named servers and their services, returns all port mappings between them as human-readable text.

Use this when the user describes their server layout and wants to know what firewall rules are needed between servers.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365') servers_json: JSON array of server definitions. Each object must have 'name' (server label) and 'services' (list of service names this server provides). Example: [ {"name": "VBR", "services": ["Backup server"]}, {"name": "Proxy", "services": ["Backup proxy"]}, {"name": "ESXi", "services": ["ESXi host"]} ] include_loopback: Include ports where source and target are the same server (default: false) exclude_subsections: Subsection names to exclude from results (e.g. ["CDP Components"]). Accepts a list or JSON string. exclude_ports: Port numbers to exclude from results (e.g. ["33035"]). Accepts a list or JSON string. format: Output format — 'json' (default), 'csv', or 'markdown'. csv and markdown return the raw content as text.

Inputs: product_name (required), servers_json (required), include_loopback, exclude_subsections, +2 more. Returns: result

get_enriched_portsA

Get port data with LLM-parsed service metadata for a product.

Returns the same port entries as get_product_ports, plus enriched metadata for each source and target service (canonical name, roles, OS, hypervisor, storage type). Useful for understanding service relationships and filtering by role.

Returns 404 if enrichment hasn't been run for this product.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365')

Inputs: product_name (required). Returns: result

get_product_portsA

Get all network port requirements for a specific Veeam product.

Returns every port entry including source service, target service, port number, protocol, and description. Use list_products first to find valid product names.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365', 'VONE')

Inputs: product_name (required). Returns: result

get_product_subheadingsA

Get the section headings that organise a product's port requirements.

Each subheading represents a component or role within the product (e.g. 'Backup Server', 'Proxy Server'). Useful for understanding the product architecture before diving into specific ports.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365')

Inputs: product_name (required). Returns: result

get_source_detailsA

Get the source services for a product, grouped by section.

Shows which components/roles (source services) exist within each section of a product's port requirements. Useful for understanding the network topology before querying specific port details.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365')

Inputs: product_name (required). Returns: result

list_productsA

List all Veeam products that have port requirement data available.

Call this first to discover valid product names before using other tools. Returns product names like 'VBR v13', 'VB365', etc.

Inputs: no named parameters. Returns: result

list_servicesA

List all known service roles for a product from the knowledge graph.

Returns canonical service names with their original name variants and any OS/hypervisor/storage qualifiers. Useful for discovering valid service names before calling generate_topology or generate_app_import.

Args: product_name: Exact product name (e.g. 'VBR v13', 'VB365')

Inputs: product_name (required). Returns: result

search_by_port_numberB

Find all Veeam product entries that use a specific port number.

Searches the port field across all products. Useful for firewall audits or checking which Veeam services need a particular port opened.

Args: port: Port number to search for (e.g. '443', '9392', '6180')

Inputs: port (required). Returns: result

search_portsA

Search across all Veeam products for port requirements matching a query.

Searches product names, source/target services, port numbers, protocols, descriptions, and section headings. Useful for questions like 'which products use SMTP' or 'what needs port 443'.

Args: query: Search text (e.g. 'SMTP', 'backup server', 'cloud gateway')

Inputs: query (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 11 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing products, querying ports, searching, and generating topologies. No two tools overlap, and descriptions clearly differentiate them.

    Naming Consistency4/5

    Names follow a consistent action_noun pattern using snake_case (list_, get_, search_, generate_). 'semantic_search' deviates slightly but remains descriptive and intuitive.

    Tool Count5/5

    With 11 tools, the server is well-scoped for its domain: discovery (list_products, list_services), detailed querying (get_product_ports, etc.), search (multiple methods), and generation (topology, app import). No bloat or insufficiency.

    Completeness5/5

    The tool set covers the full lifecycle for a read-only knowledge base: discovery, metadata browsing, precise querying, search across dimensions, and generation of outputs. No obvious gaps—users can explore and export effectively.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      C
      quality
      D
      maintenance
      Enables AI agents to control and monitor Veeam Backup & Replication v13 infrastructure through 328 MCP tools using the official REST API. Supports both stdio mode for local clients like Claude Desktop and streamable HTTP mode for remote integration with platforms like Dify.
      100
      ISC
    • A
      license
      Not graded
      quality
      C
      maintenance
      Extends Veeam Intelligence to MCP-compatible clients, enabling secure, real-time operational insight across Veeam Backup & Replication, Veeam ONE, and VSPC via natural language or AI workflows.
      22
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to interact with Veeam Backup & Replication infrastructure through natural language, allowing monitoring, management, and troubleshooting of backup jobs, sessions, and restore points.
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Aggregates network operations tools such as retrieving local network configurations and scanning ports, enabling IT professionals to perform these tasks via natural language.
      -