Network Diagram Mcp

io.github.den-indancePublished by GitHub account den-indancev1.0.7Updated Oct 27, 2026

Network topology editor — Claude builds diagrams via MCP. nmap/CSV import, one-click SSH.

The publisher's own server: Diagram

VerifiedSTDIODesktop onlyCloud & InfrastructureDeveloper Tools

Overview

AI-generated overview

Local bridge that lets an AI assistant build and edit network topology diagrams in the NetMap browser app, including nmap and CSV imports.

What you can do
  • Read and modify map state: nodes, connections, sticky notes, sheet notes and app settings
  • Search across nodes, ports, sticky notes and connection labels, or list nodes by type
  • Create, rename, switch and delete sheets, and lock a sheet against edits
  • Arrange nodes with grid, circle, force-directed or cluster layouts, and control zoom and pan
  • Import nmap XML or CSV inventories, or replace a sheet from JSON
  • Export a sheet as JSON, PNG or PDF
When to use it
Useful when you keep network topology maps in NetMap and want an assistant to draft, restructure or document them from scan output or an asset spreadsheet, rather than dragging nodes by hand.
Requirements
Runs locally via npx (Node.js). Needs an open NetMap browser tab at map.den.dance with the WebSocket bridge enabled; without it, tool calls time out. The optional NETMAP_MCP_PORT variable (default 47821) must match the port configured in NetMap settings. No login or API key.
Before you install
Many tools write to the map: adding, updating and deleting nodes, connections and stickies, clearing the map, deleting sheets and importing data that replaces sheet content. Destructive calls such as map_clear and map_delete_sheet require confirm: true. Map data lives in browser localStorage, and PNG/PDF exports return base64 the assistant must save. The package can also register OS handlers for ssh, postgres and redis links and run a local daemon with a token-gated exec endpoint.

Installation

In SourceWeft

  1. Open Network Diagram Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@den.dance/network-diagram-mcp

[npm] [smithery badge]

Visual network topology editor with AI agent integration via the Model Context Protocol. Open-source successor to netViz (netViz Inc., 1990 → CA Technologies → discontinued 2012).

Try it live → https://map.den.dance/

[NetMap workspace]

What makes it different

  • One-click ops dashboard. Click any web port (80 / 443 / 8080 / …) on a node card to open the service in a new tab. Click an SSH / Postgres / Redis port → in-app picker offers your installed clients (iTerm / Windows Terminal / psql / DBeaver / redis-cli / RDM / …) and launches the one you choose. The picker re-detects every click — newly installed clients show up immediately, never a silent locked-in default.
  • AI agents edit the map. 44 MCP tools — your Claude / Cursor / Claude Desktop session can build a diagram for you, search across nodes / ports / notes, run smart auto-layouts, export PNG / PDF — all by talking to the open browser tab.
  • nmap -oX import. Run a network scan, hand the XML to the agent, get a map with nodes auto-typed from OS fingerprint + port profile (router / switch / firewall / server / printer / …).
  • CSV inventory import. Drop in your asset spreadsheet — auto-detects columns (name / ip / type / ports / notes; aliases like hostname / description accepted).
  • Operator-grade node cards. Per-node: open ports with service names, Docker services, DNS domains, free-form notes. All searchable cross-entity via the agent.
  • Smart auto-layout. Force-directed (deterministic via seed), cluster-by-type, cluster-by-connection.
  • Multi-sheet, local-first. Multiple maps in one workspace, everything in localStorage. No login, no cloud. Export JSON / PNG / PDF.

How it works

This package is a stdio → WebSocket bridge. It runs locally as an MCP server; the live NetMap browser tab connects to it over WebSocket. The agent talks to the bridge over MCP; the bridge forwards calls to the browser, which updates React state in real time.

LLM agent (Claude Code / Claude Desktop / Cursor)   │  MCP protocol (stdio)   ▼@den.dance/network-diagram-mcp  ←  this package, runs locally   │  WebSocket ws://localhost:47821   ▼NetMap in browser (https://map.den.dance/)  ←  React state updates live

⚠️ Requires an open NetMap browser tab. Open https://map.den.dance/ — the MCP bridge is enabled by default (v1.2+), so the connection comes up as soon as the tab is open. Without an open tab the bridge has no peer and every tool call will time out. (To opt out: Settings → ⚙ → Integrations → AI Agent (MCP) → Enable WebSocket connection.)

Install

Claude Desktop

Add to claude_desktop_config.json:

json
{  "mcpServers": {    "netmap": {      "command": "npx",      "args": ["@den.dance/network-diagram-mcp"]    }  }}

Claude Code

bash
claude mcp add netmap -- npx @den.dance/network-diagram-mcp

With a custom port:

bash
claude mcp add netmap -e NETMAP_MCP_PORT=12345 -- npx @den.dance/network-diagram-mcp

Then open https://map.den.dance/ — the bridge is enabled by default (v1.2+). Settings → Integrations → AI Agent (MCP) if you need to inspect or toggle the connection. The toolbar will show a 🟢 MCP online badge when the browser and server are connected.

Verify the agent side:

bash
claude mcp list

You should see netmap in the list.

Environment variables

VarDefaultDescription
NETMAP_MCP_PORT47821Local WebSocket port the bridge listens on. Must match the URL configured in NetMap's Settings → Integrations → AI Agent (MCP).

URL Protocol Handlers + in-app client picker (v1.1+, picker since v1.2)

This package also ships an OS-level agent that registers handlers for ssh://, postgres://, and redis:// URLs. Click any such link in a browser or terminal and the agent spawns your installed client (psql / redis-cli / iTerm / Windows Terminal / kitty / DBeaver / TablePlus / RedisInsight / …).

Inside NetMap (v1.2+): when the serve daemon is running, clicking an SSH / Postgres / Redis port button on a node card opens an in-app picker of installed clients on your machine and launches the one you pick — every click re-detects, so newly installed clients show up immediately. Without the daemon, port-clicks fall back to the OS default URL handler.

Install once per machine:

bash
# Linux:   ~/.local/share/applications/netmap-<scheme>-handler.desktop + xdg-mime# macOS:   ~/Library/Application Support/NetMap/handlers/NetMap<Scheme>Handler.app + lsregister# Windows: HKCU\Software\Classes\<scheme>  (per-user, no admin)npx @den.dance/network-diagram-mcp install --all

Other CLI subcommands:

bash
npx @den.dance/network-diagram-mcp install ssh        # single schemenpx @den.dance/network-diagram-mcp uninstall postgres # remove registrationnpx @den.dance/network-diagram-mcp list               # what's registered (JSON)npx @den.dance/network-diagram-mcp detect ssh         # which clients are availablenpx @den.dance/network-diagram-mcp serve              # daemon: WS + HTTP on :47821

Click handling is daemon-less — OS routes the link to a short-lived bin/handler.js process which parses the URL, picks the first installed client (priority order: CLI → popular GUI → cross-platform power), and spawns it. The optional serve daemon adds HTTP endpoints (/status, /detect, /exec) for browser-side integration with a Bearer-token-gated /exec.

npx @den.dance/network-diagram-mcp with no args still runs the original stdio MCP server (back-compat — Smithery / Claude Desktop probes are unaffected).

Top-5 clients per scheme (priority order, first-installed wins):

SchemeClients
sshiTerm2 → Windows Terminal → GNOME Terminal → Terminal.app → kitty
postgrespsql → TablePlus → DBeaver → Beekeeper Studio → pgAdmin 4
redisredis-cli → RedisInsight → Another Redis DM → Medis → RDM (legacy)

postgresql:// aliases to postgres; rediss:// is preserved and triggers redis-cli --tls.

Available tools

State & layout

ToolDescription
map_get_stateReturn all nodes, connections, stickies, notes
map_clearClear the entire map (requires confirm: true)
map_arrangeNaive auto-arrange (grid or circle layout — ignores connections)
map_suggest_layoutSmart auto-layout: force (force-directed, deterministic via seed), cluster-by-type (lanes per type), or cluster-by-connection (BFS components into zones)

Nodes

ToolDescription
map_add_nodeAdd a node (type, name, ip, x, y)
map_update_nodeUpdate node fields by id
map_delete_nodeDelete a node and its connections
map_move_nodeMove node to new coordinates

Connections

ToolDescription
map_add_connectionAdd connection (from_id, to_id, label?, color?)
map_update_connectionUpdate label or color of a connection
map_delete_connectionDelete a connection by id

Sticky notes

ToolDescription
map_add_stickyAdd a sticky note (text, x?, y?, color?)
map_update_stickyUpdate text, color, x, y, w, h
map_delete_stickyDelete a sticky note by id
map_move_stickyMove sticky to new coordinates

Sheets (multi-sheet)

ToolDescription
map_list_sheetsList all sheets with metadata and active sheet id
map_get_sheet_dataGet nodes / connections / stickies for a sheet (default: active)
map_create_sheetCreate a new empty sheet and switch to it
map_switch_sheetSwitch active sheet by id
map_rename_sheetRename a sheet
map_delete_sheetDelete a sheet (requires confirm: true, can't delete last)

View / canvas

ToolDescription
map_set_zoomSet zoom level (0.1–3.0)
map_set_canvas_offsetPan canvas to absolute pixel position
map_zoom_to_fitAuto-fit all nodes into viewport

Lock / protection

ToolDescription
map_lock_sheetLock (locked: true) or unlock (locked: false) a sheet. Locked sheets reject all MCP mutations and disable manual editing in the UI.

Notes & settings

ToolDescription
map_get_notesGet sheet-level notes text
map_set_notesSet sheet-level notes text
map_get_settingsGet app settings (sshMode, showGrid, etc.)
map_update_settingsUpdate app settings

Search

ToolDescription
map_find_nodeStructured node-only filter by name / ip / type / text. Returns stripped {id, name, type, ip, x, y}.
map_searchFull-text cross-entity search. Looks across nodes (name / ip / notes), stickies (text), connection labels, and ports (port number + service name). Optional types: ["nodes","stickies","connections","ports"] narrows the scope.
map_get_nodes_by_typeReturn every node of a single type with FULL field data (ports, dockerServices, domains, ips, notes, parentServer, …). Use this when you need the complete objects, not the stripped projection from map_find_node.

Example — find everything matching postgres anywhere in the map:

jsonc
// → call{ "q": "postgres" }
// → result{  "nodes":       [{ "id": "n1", "name": "db-primary", "type": "server", "ip": "10.0.0.5" }],  "stickies":    [{ "id": "s2", "text": "TODO: upgrade postgres 15 → 16" }],  "connections": [{ "id": "c4", "label": "postgres replication", "from": "n1", "to": "n2" }],  "ports":       [{ "nodeId": "n1", "nodeName": "db-primary", "port": 5432, "protocol": "tcp", "service": "postgresql" }],  "total": 4}

map_search and map_get_nodes_by_type are read-only — they work on locked sheets.

Import

ToolDescription
map_import_sheetReplace active-sheet content with a provided {nodes, connections, stickies?, notes?} JSON.
map_import_nmapParse nmap -oX output (or a pre-parsed hosts[] array) and create nodes with their open ports. Auto-infers node type from OS fingerprint + port profile (router / switch / firewall / server / printer / …). Nodes auto-arranged in a square-root grid.
map_import_csvImport nodes from CSV. Auto-detects columns from the header row (name / ip / type / ports / notes — aliases like hostname / description accepted). Ports field accepts 22/tcp,80/tcp or bare numbers. Nodes laid out in a 6-column grid.

Example — turn a 2-host nmap scan into a map in one call:

jsonc
// → call{  "xml": "<?xml version=\"1.0\"?>\n<nmaprun>\n  <host>\n    <address addr=\"10.0.0.1\" addrtype=\"ipv4\"/>\n    <hostnames><hostname name=\"web.local\" type=\"user\"/></hostnames>\n    <ports>\n      <port protocol=\"tcp\" portid=\"22\"><state state=\"open\"/><service name=\"ssh\"/></port>\n      <port protocol=\"tcp\" portid=\"80\"><state state=\"open\"/><service name=\"http\"/></port>\n    </ports>\n  </host>\n  <host>\n    <address addr=\"10.0.0.2\" addrtype=\"ipv4\"/>\n    <os><osmatch name=\"Cisco IOS router\" accuracy=\"98\"/></os>\n  </host>\n</nmaprun>"}
// → result{ "count": 2, "ids": ["…", "…"] }

Provide {"hosts": [...]} instead of xml when you already have parsed host data — hosts takes priority when both are given.

Example — turn a CSV inventory snippet into a map:

jsonc
// → call{  "csv": "name,ip,type,ports,notes\ndb-primary,10.0.0.5,server,\"22/tcp,5432/tcp\",Postgres 15\nrouter-main,10.0.0.1,router,22/tcp,Edge router"}
// → result{ "count": 2, "ids": ["…", "…"] }

For non-standard headers, pass an explicit columns mapping (-1 means "absent"):

jsonc
{  "csv":     "Host,Address\nfoo,10.0.0.99",  "columns": { "name": 0, "ip": 1, "type": -1, "ports": -1, "notes": -1 }}

map_import_nmap and map_import_csv are mutations — blocked on locked sheets.

Layout

map_suggest_layout repositions every node according to a chosen algorithm; result shape: { ok: true, algorithm, changed: <node count> }.

jsonc
// Force-directed (organic; reproducible with seed){ "algorithm": "force", "iterations": 200, "seed": 42 }
// Group nodes into horizontal lanes by type{ "algorithm": "cluster-by-type" }
// Place each connected component in its own x-zone{ "algorithm": "cluster-by-connection" }

Force-directed is O(n²) per iteration — fine up to a few hundred nodes; bring iterations down for larger scenes. map_suggest_layout is a mutation — blocked on locked sheets.

Export (JSON / PNG / PDF)

ToolDescription
map_export_sheetExport a single sheet as a JSON object (auto-connections included). Legacy entry — still works.
map_exportMulti-format export: json (object), png and pdf (base64-encoded blob + mimeType).
jsonc
// JSON{ "format": "json" }// → { format: "json", data: { nodes, connections, stickies, notes, auto_connections } }
// PNG (max 30 s; agent must persist the base64 to a file){ "format": "png" }// → { format: "png", filename: "netmap-<sheetId>.png",//      base64: "iVBORw0KGgoAAAANSUhEUg…",//      mimeType: "image/png" }
// PDF{ "format": "pdf" }// → { format: "pdf", filename: "netmap-<sheetId>.pdf",//      base64: "JVBERi0xLjQK…",//      mimeType: "application/pdf" }

PNG / PDF capture renders the live workspace via html-to-image + jsPDF, so the MCP server raises the per-command timeout to 30 s for this tool. map_export is read-only — works on locked sheets.

Connection status indicator

A badge appears next to the NetMap version in the toolbar (click it to open Settings):

BadgeMeaning
🟢 MCP onlineConnected — agent can edit the map
🟡 MCPConnecting to server
🟠 MCP retry N/10Retrying, up to 10 attempts × 30 sec
🔴 MCP errorGave up — start the server, then toggle off / on to retry
(no badge)Disabled in settings

Detailed status (with URL and hints) is shown inside Settings → Integrations → AI Agent (MCP).

Running from source (for contributors)

bash
git clone https://github.com/den-indance/network-diagram-mcp.gitcd network-diagram-mcpnpm installnode index.js

Override port: NETMAP_MCP_PORT=12345 node index.js.

Register the local build in Claude Code instead of npm:

bash
claude mcp add netmap-dev -- node /absolute/path/to/network-diagram-mcp/index.js

License

MIT — see LICENSE.

Source: README.md at commit f9a3503

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.7LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Diagram integrations