MCP server for controlling Draw.io and diagrams.net diagrams from Claude, including document discovery, page management, layers, shapes, edges, Mermaid import, diagram import/export, and a built-in editor mode.
Draw.io MCP Server can create, edit, delete, import, export, rename, copy, and reorganize diagram pages, layers, shapes, edges, labels, metadata, and Mermaid-derived content., Live operations target connected Draw.io browser tabs or the built-in editor; verify the selected document and page before allowing destructive edits., The server can run local HTTP and WebSocket endpoints, optionally with TLS or auto-generated self-signed certificates; avoid binding it to untrusted network interfaces., Browser-extension mode links a browser tab to the MCP server, so only connect tabs containing diagrams that the agent is allowed to inspect or modify., Export tools can write or return XML, SVG, and PNG files with embedded diagram data; review outputs before sharing them externally., Use trusted package sources, pin versions for repeatable workflows, and review generated diagrams before committing architectural or security documentation.
Privacy notes
Diagrams can include private architecture, network topology, cloud account names, customer systems, credentials embedded in labels, incident details, internal process maps, or product plans., The MCP client can receive diagram XML, SVG, PNG exports, page names, layer names, selected-cell data, shape metadata, browser tab document metadata, and imported Mermaid content., Local editor and browser-extension workflows may leave diagrams, exported files, browser state, TLS material, and logs on disk., Treat exported SVG or PNG files with embedded XML as source files, because they can contain full editable diagram data beyond the visible image., Clear temporary files, generated certificates, and MCP logs when they are no longer needed for the diagram workflow.
Author
Lukas Gazo
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
6 safety and 5 privacy notes across 5 risk areas. Review closely: credentials & tokens, network access.
5 areas
SafetyGeneralDraw.io MCP Server can create, edit, delete, import, export, rename, copy, and reorganize diagram pages, layers, shapes, edges, labels, metadata, and Mermaid-derived content.
SafetyExecution & processesLive operations target connected Draw.io browser tabs or the built-in editor; verify the selected document and page before allowing destructive edits.
SafetyNetwork accessThe server can run local HTTP and WebSocket endpoints, optionally with TLS or auto-generated self-signed certificates; avoid binding it to untrusted network interfaces.
SafetyGeneralBrowser-extension mode links a browser tab to the MCP server, so only connect tabs containing diagrams that the agent is allowed to inspect or modify.
SafetyLocal filesExport tools can write or return XML, SVG, and PNG files with embedded diagram data; review outputs before sharing them externally.
SafetyGeneralUse trusted package sources, pin versions for repeatable workflows, and review generated diagrams before committing architectural or security documentation.
PrivacyCredentials & tokensDiagrams can include private architecture, network topology, cloud account names, customer systems, credentials embedded in labels, incident details, internal process maps, or product plans.
PrivacyLocal filesLocal editor and browser-extension workflows may leave diagrams, exported files, browser state, TLS material, and logs on disk.
PrivacyLocal filesTreat exported SVG or PNG files with embedded XML as source files, because they can contain full editable diagram data beyond the visible image.
PrivacyLocal filesClear temporary files, generated certificates, and MCP logs when they are no longer needed for the diagram workflow.
Disclosure: Community-maintained open source MCP server for Draw.io/diagrams.net, published as the `drawio-mcp-server` npm package under the MIT license.
Safety notes
Draw.io MCP Server can create, edit, delete, import, export, rename, copy, and reorganize diagram pages, layers, shapes, edges, labels, metadata, and Mermaid-derived content.
Live operations target connected Draw.io browser tabs or the built-in editor; verify the selected document and page before allowing destructive edits.
The server can run local HTTP and WebSocket endpoints, optionally with TLS or auto-generated self-signed certificates; avoid binding it to untrusted network interfaces.
Browser-extension mode links a browser tab to the MCP server, so only connect tabs containing diagrams that the agent is allowed to inspect or modify.
Export tools can write or return XML, SVG, and PNG files with embedded diagram data; review outputs before sharing them externally.
Use trusted package sources, pin versions for repeatable workflows, and review generated diagrams before committing architectural or security documentation.
Privacy notes
Diagrams can include private architecture, network topology, cloud account names, customer systems, credentials embedded in labels, incident details, internal process maps, or product plans.
The MCP client can receive diagram XML, SVG, PNG exports, page names, layer names, selected-cell data, shape metadata, browser tab document metadata, and imported Mermaid content.
Local editor and browser-extension workflows may leave diagrams, exported files, browser state, TLS material, and logs on disk.
Treat exported SVG or PNG files with embedded XML as source files, because they can contain full editable diagram data beyond the visible image.
Clear temporary files, generated certificates, and MCP logs when they are no longer needed for the diagram workflow.
Prerequisites
Node.js 22 or newer for the published npm package.
An MCP client such as Claude Desktop or Claude Code.
A browser for the built-in editor, or the Draw.io MCP browser extension when controlling an existing diagrams.net tab.
Review of which diagrams, browser tabs, pages, and export locations Claude is allowed to modify.
TLS planning when using Firefox, browser-extension WebSocket connections, reverse proxies, or network-accessible transports.
Schema details
Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Tool listing metadata
Disclosure
Community-maintained open source MCP server for Draw.io/diagrams.net, published as the `drawio-mcp-server` npm package under the MIT license.
Draw.io MCP Server lets Claude control Draw.io and diagrams.net diagrams through
MCP. It can inspect connected documents, work across pages and layers, add and
edit shapes or edges, import Mermaid diagrams, export XML/SVG/PNG files, and run
a built-in editor without requiring a separate browser extension.
Use it when Claude needs supervised access to create or maintain architecture
diagrams, flowcharts, cloud diagrams, process maps, or visual documentation in a
Draw.io-compatible format.
These sources were reviewed on 2026-06-06. Prefer the live repository,
README, npm metadata, license, package manifests, configuration guide, tools
reference, server entrypoint, and tool registry for current setup and behavior
details.
Features
Run a built-in Draw.io editor from the MCP server.
Connect to Draw.io or diagrams.net browser tabs through the companion
extension.
List connected documents and target a specific document in multi-tab
workflows.
claude mcp add-json drawio '{"type":"stdio","command":"npx","args":["-y","drawio-mcp-server","--editor"]}'
After the MCP server starts, open the local editor URL printed by the server or
configure the browser extension to connect to the matching WebSocket settings.
Use Cases
Generate an architecture diagram from a written system description.
Convert Mermaid diagrams into editable Draw.io pages.
Add cloud, network, or Cisco stencil shapes to infrastructure diagrams.
Create a multi-page visual design document from separate agent tasks.
Inspect a diagram's pages, layers, selected cells, and exported XML.
Update labels, connectors, layer organization, or metadata in an existing
Draw.io file.
Export diagrams for review while preserving embedded editable XML.
Safety and Privacy
Draw.io MCP Server can mutate diagrams directly. Confirm the connected document,
target page, and cell IDs before running edits, especially when multiple tabs or
agents are active.
Architecture diagrams often reveal sensitive implementation details. Keep
diagram XML, embedded SVG/PNG exports, browser-extension state, generated TLS
material, and MCP logs within approved storage, and review all generated visuals
before publishing or committing them.
Show that Draw.io MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/drawio-mcp-server)
How it compares
Draw.io MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
MCP server for controlling Draw.io and diagrams.net diagrams from Claude, including document discovery, page management, layers, shapes, edges, Mermaid import, diagram import/export, and a built-in editor mode.
Official Agentset MCP server that lets Claude retrieve cited knowledge-base results from an Agentset namespace through the `knowledge-base-retrieve` tool, with optional tenant scoping and custom tool descriptions.
MCP server for Anki flashcards that lets Claude review cards, manage decks, create and update notes, handle tags and media, inspect stats, and drive Anki desktop GUI workflows.
✓Draw.io MCP Server can create, edit, delete, import, export, rename, copy, and reorganize diagram pages, layers, shapes, edges, labels, metadata, and Mermaid-derived content.
Live operations target connected Draw.io browser tabs or the built-in editor; verify the selected document and page before allowing destructive edits.
The server can run local HTTP and WebSocket endpoints, optionally with TLS or auto-generated self-signed certificates; avoid binding it to untrusted network interfaces.
Browser-extension mode links a browser tab to the MCP server, so only connect tabs containing diagrams that the agent is allowed to inspect or modify.
Export tools can write or return XML, SVG, and PNG files with embedded diagram data; review outputs before sharing them externally.
Use trusted package sources, pin versions for repeatable workflows, and review generated diagrams before committing architectural or security documentation.
✓The MCP server sends Claude's retrieval queries to the Agentset API using the configured API key and namespace.
The `knowledge-base-retrieve` tool can return up to 100 results per call and can rerank results by relevance.
Namespace and tenant selection control which indexed documents are searchable; review them before connecting a shared agent.
API keys should be scoped, rotated, and stored only in the MCP server environment or a secret manager.
Custom tool descriptions can influence when the model calls the retrieval tool, so review them before use in production workflows.
✓AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files.
Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access.
The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces.
Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events.
Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data.
Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls.
✓Anki MCP Server can create, update, delete, move, tag, rate, and sync cards and notes through AnkiConnect.
Destructive tools include note deletion, media deletion, unused-tag clearing, deck moves, tag replacement, model styling changes, and review rating actions that affect scheduling.
The server supports read-only mode that blocks exposed write actions, but users should still review tool calls before enabling unrestricted study or collection-management workflows.
Media tools can store files from local paths, URLs, or base64 data and can retrieve media as base64 content.
GUI tools can open Anki windows, select cards, edit notes, show answers, and undo the last Anki action.
Remote tunnel or ngrok-style setups expose local Anki to cloud-hosted AI clients and require careful authentication, origin, and URL-sharing controls.
Privacy notes
✓Diagrams can include private architecture, network topology, cloud account names, customer systems, credentials embedded in labels, incident details, internal process maps, or product plans.
The MCP client can receive diagram XML, SVG, PNG exports, page names, layer names, selected-cell data, shape metadata, browser tab document metadata, and imported Mermaid content.
Local editor and browser-extension workflows may leave diagrams, exported files, browser state, TLS material, and logs on disk.
Treat exported SVG or PNG files with embedded XML as source files, because they can contain full editable diagram data beyond the visible image.
Clear temporary files, generated certificates, and MCP logs when they are no longer needed for the diagram workflow.
✓Retrieved chunks can include private documents, product specs, policies, support content, internal procedures, historical project information, or customer-specific data.
Retrieval queries, namespace IDs, tenant IDs, document chunks, citations, and tool outputs may be visible to the MCP client, model provider, Agentset logs, and application telemetry.
Tenant IDs are useful for data segregation, but incorrect tenant or namespace configuration can expose the wrong knowledge base.
Do not paste API keys, namespace IDs, tenant IDs, or retrieved private chunks into shared issue reports, screenshots, or repository files.
✓Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state.
MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details.
Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data.
Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content.
Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions.
✓Tool calls can expose deck names, note fields, card contents, tags, review history, media filenames, base64 media, selected notes, collection stats, scheduling metadata, and AnkiConnect errors.
Flashcards may contain medical, language-learning, school, work, personal, customer, or confidential study material.
Sync can send Anki collection changes to AnkiWeb according to the user's Anki account and sync settings.
Local media file paths, URLs imported into cards, and GUI-selected note IDs can enter MCP client context and model logs.
Remote tunnel providers and hosted clients may process connection metadata or traffic according to their own policies.
Prerequisites
Node.js 22 or newer for the published npm package.
An MCP client such as Claude Desktop or Claude Code.
A browser for the built-in editor, or the Draw.io MCP browser extension when controlling an existing diagrams.net tab.
Review of which diagrams, browser tabs, pages, and export locations Claude is allowed to modify.
Agentset account or self-hosted Agentset deployment with a populated namespace.
Agentset API key with access to the namespace Claude should query.
Node.js 18.17 or newer for running the `@agentset/mcp` package.
Namespace ID selected with `--ns` or `AGENTSET_NAMESPACE_ID`.
Unity project using Unity 2022.3 or newer for the current package metadata.
Unity Hub or a local Unity Editor installation.
Node.js 20.19 or newer, or Node.js 22.12 or newer, for `unity-mcp-cli`.
An MCP client such as Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, GitHub Copilot, Cline, or another supported client.
Anki Desktop installed and running.
The AnkiConnect add-on installed in Anki.
Node.js 22.12 or newer for the npm package path.
Review of which decks, cards, tags, media files, and note types the MCP client may access.
Install
npx -y drawio-mcp-server --editor
Run `npx @agentset/mcp --ns <namespace-id>` with `AGENTSET_API_KEY` set in the MCP server environment.