Routed, editable network diagrams from CDP/LLDP output, CSV or Graphviz DOT, as draw.io files
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Generate a routed, laid-out network diagram from topology text (Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory — every format is listed in the drawbridge://guide resource) and export it. Drawbridge decides where the lines go; you decide what connects to what. HOW TO GET A PRECISE RESULT: device output the user pasted IS the source — pass it unchanged, never rewritten as DOT. When you write DOT yourself: set `kind=` on EVERY device so it draws as the real thing rather than a neutral box (firewall, waf, ips, vpn-gateway, proxy, nac, router, switch, l3-switch, load-balancer, wifi-ap, wlc, … — full list in the drawbridge://guide resource). Put `speed=` on every cable ("10G", "1G"), and `link=` where the cable MEANS something (ipsec, trunk, lag, wan, mgmt, wireless, conduit, fieldbus, ha). Never set `pos=`, `width=` or `height=`: Drawbridge lays out and routes — placing devices yourself is what makes a diagram look generated. READ THE `notes` IN THE RESULT AND FIX YOUR SOURCE: they name each line that was skipped or adjusted, and an unrecognised kind silently becomes a plain box otherwise. Iterate until the notes are empty. CHOOSING `kind`: `drawio` when the user will open or edit the drawing (this is usually what they want, and it is the only one they can change); `svg` to embed in a document or a page; `png` to show inline in a chat; `describe.json` to READ a drawing back and reason about it; `csv` / `netbox.csv` for a cable schedule and `netbox-devices.csv` for the hardware; `dot` to hand the topology on; `clab.yml` to turn the design into a Containerlab topology you can deploy. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
Topology text: Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory. Device output goes in exactly as the user pasted it — do not rewrite it as DOT.
Output format. Defaults to svg.
Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name.
Render theme. Omit to follow the OS appearance; pin it for machine-independent output.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http drawbridge https://drawbridge.fortiknight.com/mcp
Generate a routed, laid-out network diagram from topology text (Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory — every format is listed in the drawbridge://guide resource) and export it. Drawbridge decides where the lines go; you decide what connects to what. HOW TO GET A PRECISE RESULT: device output the user pasted IS the source — pass it unchanged, never rewritten as DOT. When you write DOT yourself: set `kind=` on EVERY device so it draws as the real thing rather than a neutral box (firewall, waf, ips, vpn-gateway, proxy, nac, router, switch, l3-switch, load-balancer, wifi-ap, wlc, … — full list in the drawbridge://guide resource). Put `speed=` on every cable ("10G", "1G"), and `link=` where the cable MEANS something (ipsec, trunk, lag, wan, mgmt, wireless, conduit, fieldbus, ha). Never set `pos=`, `width=` or `height=`: Drawbridge lays out and routes — placing devices yourself is what makes a diagram look generated. READ THE `notes` IN THE RESULT AND FIX YOUR SOURCE: they name each line that was skipped or adjusted, and an unrecognised kind silently becomes a plain box otherwise. Iterate until the notes are empty. CHOOSING `kind`: `drawio` when the user will open or edit the drawing (this is usually what they want, and it is the only one they can change); `svg` to embed in a document or a page; `png` to show inline in a chat; `describe.json` to READ a drawing back and reason about it; `csv` / `netbox.csv` for a cable schedule and `netbox-devices.csv` for the hardware; `dot` to hand the topology on; `clab.yml` to turn the design into a Containerlab topology you can deploy. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
| Argument | Type | Description |
|---|---|---|
| kind | string | Output format. Defaults to svg. |
| name | string | Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name. |
| theme | string | Render theme. Omit to follow the OS appearance; pin it for machine-independent output. |
| source* | string | Topology text: Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory. Device output goes in exactly as the user pasted it — do not rewrite it as DOT. |
{
"type": "object",
"required": [
"source"
],
"properties": {
"kind": {
"enum": [
"svg",
"png",
"drawio",
"dot",
"csv",
"netbox.csv",
"netbox-devices.csv",
"describe.json",
"clab.yml"
],
"type": "string",
"description": "Output format. Defaults to svg."
},
"name": {
"type": "string",
"description": "Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name."
},
"theme": {
"enum": [
"light",
"dark"
],
"type": "string",
"description": "Render theme. Omit to follow the OS appearance; pin it for machine-independent output."
},
"source": {
"type": "string",
"description": "Topology text: Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory. Device output goes in exactly as the user pasted it — do not rewrite it as DOT."
}
},
"additionalProperties": false
}Read a Drawbridge/draw.io network diagram and return its contents as structured JSON: devices, links, pages, layers and groups — for auditing or querying an existing drawing. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
| Argument | Type | Description |
|---|---|---|
| document* | string | The .drawio document as XML text. |
{
"type": "object",
"required": [
"document"
],
"properties": {
"document": {
"type": "string",
"description": "The .drawio document as XML text."
}
},
"additionalProperties": false
}CHANGE AN EXISTING DIAGRAM instead of regenerating it: add, update and remove devices and links in a .drawio document and get the edited document back. This is the tool for "add a switch to this drawing" — `create_diagram` would redraw the whole page and throw away every position a human placed by hand. Call `describe` first to get the ids, then name them here. Everything you do not name keeps its exact position. Do NOT set x/y on a new device: Drawbridge places what you add below the existing drawing, which is the whole point of using this rather than editing the XML. Say what a new device belongs UNDER with `near`, naming a device already in the drawing: it lands straight below that one, in free space, so use it on every device you are about to cable to something. Put cables in an aggregate with `bundle` on add_edge or update_edge — its name, "ae1": cables given one name share one ring, and a ring of that name already drawn is joined. A cable already in another ring is added to this one; to move it, send bundle "" first and then the new name, in the same call. Set `kind` on every device you add or it draws as a plain box, and read the `notes` in the result — a mistyped id skips that one op and says so rather than failing the batch. The result names the ids it minted, in op order. Every id in an op must already exist when you send it — an op cannot name something an earlier op in the same call created, so adding a device and cabling it is two calls: add it, read the ids, then wire them. It writes nothing: save the returned document yourself, as it is — a cable or a position you write into the XML by hand skips the routing and the checks this tool makes. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
| Argument | Type | Description |
|---|---|---|
| ops* | array | The changes to apply, in order. Send a whole thought at a time rather than an op per call. |
| kind | string |
Render a Drawbridge/draw.io network diagram to an output format (svg, png, drawio, dot, csv, netbox.csv, netbox-devices.csv, describe.json, clab.yml). Returns the exported content. CHOOSING `kind`: `drawio` when the user will open or edit the drawing (this is usually what they want, and it is the only one they can change); `svg` to embed in a document or a page; `png` to show inline in a chat; `describe.json` to READ a drawing back and reason about it; `csv` / `netbox.csv` for a cable schedule and `netbox-devices.csv` for the hardware; `dot` to hand the topology on; `clab.yml` to turn the design into a Containerlab topology you can deploy. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
| Argument | Type | Description |
|---|---|---|
| kind | string | Output format. Defaults to svg. |
| name | string | Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name. |
| theme | string | Render theme. Omit to follow the OS appearance; pin it for machine-independent output. |
| document* | string | The .drawio document as XML text. |
{
"type": "object",
"required": [
"document"
],
"properties": {
"kind": {
"enum": [
"svg",
"png",
"drawio",
"dot",
"csv",
"netbox.csv",
"netbox-devices.csv",
"describe.json",
"clab.yml"
],
"type": "string",
"description": "Output format. Defaults to svg."
},
"name": {
"type": "string",
"description": "Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name."
},
"theme": {
"enum": [
"light",
"dark"
],
"type": "string",
"description": "Render theme. Omit to follow the OS appearance; pin it for machine-independent output."
},
"document": {
"type": "string",
"description": "The .drawio document as XML text."
}
},
"additionalProperties": false
}CHECK TOPOLOGY TEXT BEFORE DRAWING IT: reads the same source `create_diagram` would and reports what it found — the format it detected, how many devices and links it would draw, and every line it would skip or adjust, with the line number and the reason. An unknown `kind=` names the nearest real one. Nothing is laid out, routed or rendered, so it is far cheaper than a draw: call it, fix what it names, then call `create_diagram` once. Results carry `name`: a suggested basename for this diagram. Write every file for one diagram into its own directory named after it — <name>/<name>.drawio, <name>/<name>.svg, <name>/<name>.cables.csv — so two diagrams never share a directory.
| Argument | Type | Description |
|---|---|---|
| source* | string | Topology text: Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory. Device output goes in exactly as the user pasted it — do not rewrite it as DOT. |
{
"type": "object",
"required": [
"source"
],
"properties": {
"source": {
"type": "string",
"description": "Topology text: Graphviz DOT, Mermaid, CSV, CDP/LLDP neighbour output from most switch vendors, a FortiLink topology dump, Containerlab, Meraki or UniFi JSON, or an Ansible inventory. Device output goes in exactly as the user pasted it — do not rewrite it as DOT."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.
| Output format for the edited document. Defaults to drawio, which is what you want: it is the file the user keeps working on. |
| name | string | Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name. |
| theme | string | Render theme. Omit to follow the OS appearance; pin it for machine-independent output. |
| document* | string | The .drawio document as XML text. |
{
"type": "object",
"required": [
"document",
"ops"
],
"properties": {
"ops": {
"type": "array",
"items": {
"type": "object",
"required": [
"op"
],
"properties": {
"h": {
"type": "number",
"description": "Height in scene units. Omit for the default size."
},
"w": {
"type": "number",
"description": "Width in scene units. Omit for the default size."
},
"x": {
"type": "number",
"description": "Left edge in scene units. OMIT IT: Drawbridge places what you add below the existing drawing, or under the device `near` names. Only set it to move a device you name by id."
},
"y": {
"type": "number",
"description": "Top edge in scene units, increasing DOWNWARDS. OMIT IT — see `x`."
},
"id": {
"type": "string",
"description": "The existing device or link to change — required by update_node, remove_node, update_edge and remove_edge. Ids come from `describe`."
},
"op": {
"enum": [
"add_node",
"update_node",
"remove_node",
"add_edge",
"update_edge",
"remove_edge"
],
"type": "string",
"description": "What this op does. Every other field belongs to one of these."
},
"to": {
"type": "string",
"description": "Target device id — required by add_edge. Already existing, as for `from`."
},
"cidr": {
"type": "string",
"description": "Subnet annotation for a zone, e.g. \"10.20.30.0/24\"."
},
"from": {
"type": "string",
"description": "Source device id — required by add_edge. A device that already exists: not one an earlier op in this call added, whose id comes back only in the result."
},
"kind": {
"type": "string",
"description": "What the device IS (firewall, switch, router, server, ap, cloud, …) — required by add_node. Read `drawbridge://kinds` for the full vocabulary. Without it the device draws as a plain box."
},
"link": {
"type": "string",
"description": "What the link MEANS: ipsec, trunk, lag, wan, mgmt, wireless, conduit, fieldbus, ha. Empty clears it."
},
"near": {
"type": "string",
"description": "Optional on add_node: the id of a device ALREADY in the drawing that the new one belongs under. Drawbridge places it straight below that device in free space, so the cable you add next runs the way a person would have drawn it. Use it whenever you are about to cable the new device to something; without it the device lands below the whole drawing. Ids come from `describe` — an op cannot name a device an earlier op in the same call added, and an unknown id skips the op and says so."
},
"role": {
"type": "string",
"description": "Placement band tag for the device (EDGE, CORE, ACCESS, …)."
},
"vlan": {
"type": "string",
"description": "What the link carries, e.g. \"10,20,30 native 1\"."
},
"color": {
"type": "string",
"description": "Hex accent color override. Omit to keep the shape family’s own color."
},
"label": {
"type": "string",
"description": "The name shown on the device, or the midpoint label on a link."
},
"speed": {
"type": "string",
"description": "Link speed, e.g. \"1G\", \"10G\" — drives the stroke."
},
"bundle": {
"type": "string",
"description": "Optional on add_edge and update_edge: the aggregate (LAG, port-channel) the cable is in, by NAME — its ring’s caption, e.g. \"ae1\" or \"Po1\". Every cable this call names with one name shares ONE ring, and a ring of that caption already drawn is joined: one a named cable is in, or the one the cable shares a device with — so adding a third uplink to \"ae1\" is an add_edge with bundle \"ae1\". Cables that would share no device are refused and named in notes. A cable already in another ring is ADDED to this one — a cable can be in a ring at each end — so to MOVE it, send update_edge with bundle \"\" and then the new name, in the same call. On update_edge an empty string takes the cable out of every ring it is in. `describe` reads it back as the link’s `aggregates`."
},
"length": {
"type": "string",
"description": "How long the cable is, e.g. \"3 m\". A copper run longer than its standard allows is refused and named in notes."
},
"medium": {
"type": "string",
"description": "What the cable IS: rj45, dac, aoc, mmf, smf, smf-long, bidi, cwdm, dwdm, breakout-dac, breakout-mpo, rj45-sfp. Drives the optics count. Empty clears it."
},
"module": {
"type": "string",
"description": "The single-mode module the cable takes, e.g. \"FR1\" or \"LR1\" — one its speed and medium offer; anything else is refused and the choices named in notes."
},
"circuit": {
"type": "string",
"description": "The carrier’s reference for the service."
},
"toLabel": {
"type": "string",
"description": "Port label at the target end, e.g. \"wan1\"."
},
"provider": {
"type": "string",
"description": "The carrier, e.g. \"Telia\"."
},
"quantity": {
"type": "string",
"description": "How many identical cables this ONE line stands for, e.g. \"8\" for eight 25G DACs from one server to one switch — a whole number from 2 to 999 (\"1\" or \"\" is one cable; a number is read too). Give the port fields a range that names that many, \"eno1-8\". Anything else is refused and named in notes."
},
"fromLabel": {
"type": "string",
"description": "Port label at the source end, e.g. \"ge-0/0/1\"."
},
"functions": {
"type": "array",
"items": {
"type": "string"
},
"description": "What the device RUNS, e.g. [\"VPN\", \"IPS\"]."
},
"installed": {
"type": "boolean",
"description": "The cable has actually been run (the schedule’s tick); false clears it."
},
"lineStyle": {
"type": "string",
"description": "A Normal cable’s own line: solid, dashed or dotted. Only on a cable with no link type — refused, and named in notes, on one that has one. Empty clears it, and the cable follows the drawing’s Cable line again."
},
"toAddress": {
"type": "string",
"description": "The address at the target end, e.g. \"10.0.0.2/30\"."
},
"wavelength": {
"type": "string",
"description": "An optical cable’s wavelength or WDM channel, e.g. \"1310 nm\" or \"C21\". Refused, and named in notes, on a cable whose medium has none (copper, DAC, AOC)."
},
"fromAddress": {
"type": "string",
"description": "The address at the source end, e.g. \"10.0.0.1/30\"."
},
"quantityHidden": {
"type": "boolean",
"description": "Hide the ×N mark on the drawing; every count still says N."
}
},
"additionalProperties": false
},
"maxItems": 10000,
"minItems": 1,
"description": "The changes to apply, in order. Send a whole thought at a time rather than an op per call."
},
"kind": {
"enum": [
"svg",
"png",
"drawio",
"dot",
"csv",
"netbox.csv",
"netbox-devices.csv",
"describe.json",
"clab.yml"
],
"type": "string",
"description": "Output format for the edited document. Defaults to drawio, which is what you want: it is the file the user keeps working on."
},
"name": {
"type": "string",
"description": "Basename to use for this diagram instead of the one derived from its content. Slugified; wins over the document’s own name."
},
"theme": {
"enum": [
"light",
"dark"
],
"type": "string",
"description": "Render theme. Omit to follow the OS appearance; pin it for machine-independent output."
},
"document": {
"type": "string",
"description": "The .drawio document as XML text."
}
},
"additionalProperties": false
}