draw.io MCP server
io.draw/mcpdraw.iostreamable-httpv1.10.0Scanned
Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.
4 tools: 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the draw.io MCP server can do
The draw.io MCP server is published by draw.io, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: create_diagram and create_semantic_diagram), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (search_shapes).
The fixed checks matched 3 findings (long-description and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 17, 2026, version 1.10.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 2Claude Code: ask
create_diagramCreates and displays an interactive draw.io diagram from Mermaid.js syntax or draw.io XML — provide exactly one.2 findings
Why it is in this group
- The name "create_diagram" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description is 2,033 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...t) and set `routing: "libavoid"` only when an edge would otherwise cross a shape."
- Warn
The server marks "create_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_diagram" says "create": a word for a change.
Description, as the server wrote it Creates and displays an interactive draw.io diagram from Mermaid.js syntax or draw.io XML — provide exactly one. **Choose the format first.** Use `xml` for diagrams of boxes and lines up to about 30 shapes: flowcharts, pipelines, decision trees, org charts, ER schemas, UML class, state and use case diagrams, mind maps, timelines, architecture, cloud and network diagrams, swimlanes, UI mockups, floor plans and anything with stencils. You place every shape yourself, laid out for the chat view (see the XML reference). Use `mermaid` for sequenceDiagram, gantt, gitGraph, pie, journey, quadrantChart, xychart-beta, sankey-beta, requirementDiagram, C4Context/C4Container/C4Component, block-beta, packet-beta, kanban, radar-beta, treemap-beta, treeView-beta, venn-beta, ishikawa-beta, zenuml, wardley-beta, eventmodeling, and for flowcharts, class and state diagrams of more than about 30 shapes (flowcharts with postLayout elk). Whenever the user asks for draw.io XML or no Mermaid, use XML for the rest of the conversation. **Call `get_drawio_reference` before your first diagram in a conversation**, once per format, with the format you chose: "mermaid" has the syntax for every type (a misspelled header renders blank), "xml" the styles, layout grid, edges, containers, layers and dark mode. For AWS, Azure, GCP and Kubernetes icons write `icon=aws lambda` in the style; call `search_shapes` first for other industry icons (Cisco, P&ID, electrical) or logos. XML essentials: <mxGraphModel adaptiveColors="auto"><root><mxCell id="0"/><mxCell id="1" parent="0"/>…</root></mxGraphModel>. Every cell has a unique id. Vertices: vertex="1" with <mxGeometry x y width height as="geometry"/>. Edges: edge="1" with source and target, always with a child <mxGeometry relative="1" as="geometry"/>. Put html=1 in every style and XML-escape HTML in values (< > & "). No XML comments. Don't add waypoints. Place the shapes yourself (no postLayout) and set `routing: "libavoid"` only when an edge would otherwise cross a shape.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_semantic_diagramOnly for a diagram the user explicitly asked to get fast or cheap: a quick, fast or rough diagram, a sketch or a draft, little effort or few tokens, in any language ("schnell", "Sk…1 finding
Why it is in this group
- The name "create_semantic_diagram" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "create_semantic_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_semantic_diagram" says "create": a word for a change.
Description, as the server wrote it Only for a diagram the user explicitly asked to get fast or cheap: a quick, fast or rough diagram, a sketch or a draft, little effort or few tokens, in any language ("schnell", "Skizze", "wenig Aufwand", "sparsam"). A request without such words, however simple the diagram, goes to create_diagram, never here, and so do the types not listed here: create_diagram places the shapes with more care. A change to a diagram drawn here comes back here. Creates and displays a draw.io diagram from a description of its content: you say what exists and how it connects, the server lays it out, routes the lines and styles it. Never give coordinates, sizes or styles. To change the diagram, call this again with the whole changed description, keeping the ids, the cells of what stays and the layout. Arguments: type, title, nodes, edges, groups; their keys are in the schema. type "flowchart" (processes, with or without swimlanes): nodes are steps with a kind (start, end, step, decision, error, data); for swimlanes, groups are the lanes in order and each node names its lane in group; edges are transitions, labeled on the branches of a decision ("Yes", "No"). End every path at an end node. Placement: give every node row and col, its cell in one grid for the whole diagram: at most 6 cols, a large diagram grows down, to 8 rows. A group's nodes form a block of cells of their own, which the server frames. A lane is a row (or a column) of that grid, col (or row) the step.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
get_drawio_referenceReturns the draw.io diagram generation reference as Markdown.No findings
Why it is in this group
- The name "get_drawio_reference" says "get": a word for reading.
Description, as the server wrote it Returns the draw.io diagram generation reference as Markdown. Format "xml": styles, the layout grid, edges, containers, swimlanes, layers, tags, metadata, dark mode, the layout and routing passes, and the well-formedness rules for create_diagram's xml. Format "mermaid": the header keyword and syntax hints for every Mermaid type draw.io supports, flowchart styling and the ELK layout. Call it once per format and conversation, before the first diagram in that format; the reference stays valid for the rest of the conversation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_shapesSearch the draw.io shape library by keywords.Reads text others writeNo findings
Why it is in this group
- The name "search_shapes" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search the draw.io shape library by keywords. Returns matching shapes with their exact style strings, dimensions, and titles. Covers ~10,000 built-in stencils (cloud architecture, network topology, P&ID, electrical, Cisco, Kubernetes, BPMN) and, when those are sparse, supplements results with the draw.io icon service (brand/product logos and general-purpose concept icons, e.g. 'react', 'slack', 'shopping cart', 'solar panel'). Use ONLY for diagrams that need industry-specific, branded, or pictorial icons. Do NOT use for standard diagram types like flowcharts, UML, ERD, org charts, or mind maps — these use basic geometric shapes (rectangles, diamonds, circles, cylinders) that are already covered in the XML reference. Also skip if the user asks to use basic/simple shapes or says not to search. The style string from the results can be used directly in mxCell style attributes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:55 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.draw.io/mcp: tools/list returned 4 tools to an anonymous client, including create_diagram (write), create_semantic_diagram (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 1 to 2
Findings
Matches of fixed checks, with the text they matched.
- Warncreate_diagram
The server marks "create_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_diagram" says "create": a word for a change.
The server marks "create_semantic_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_semantic_diagram" says "create": a word for a change.
- Infocreate_diagram
The description is 2,033 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...t) and set `routing: "libavoid"` only when an edge would otherwise cross a shape."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
- Tools that change things, listed without credentials: 1 to 2
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:create_semantic_diagramChanges things
- Changed:create_diagramChanges thingsdescription
Install
Pinned to version 1.10.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http draw https://mcp.draw.io/mcpclaude mcp add --transport http draw https://mcp.draw.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__draw__search_shapes",
"mcp__draw__get_drawio_reference"
],
"ask": [
"mcp__draw__create_diagram",
"mcp__draw__create_semantic_diagram"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as draw. Review it before you use it.
Capability tags behind 1 rule
- mcp__draw__search_shapes untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.draw/mcp/verify?hash=0a16474220770e776fa65d5c1cfc0d49da2e6bb83e0d877c3393f489bf300fe5" | jq -e '.changed == false'Pinned hash 0a1647422077, from Nov 17, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.draw/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.draw/mcp)Source: MCP Registry · repository. Synced Nov 17, 2026, 06:17 UTC.
draw.io MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the draw.io MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the draw.io MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the draw.io MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the draw.io MCP server have?
- 4 tools: 2 write, 2 read. create_diagram, create_semantic_diagram, search_shapes and get_drawio_reference.
Does the draw.io MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the draw.io MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the draw.io MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.