Mind Map MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Mind Map MCP break this launch plan down as a mind map"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mind Map MCP
Mind maps and flowcharts in your AI chat. When an answer would be a long list or a wall of tickets, the AI draws it as a diagram instead. You restyle it, edit it and comment on it, and the AI is told what you did.

Watch the full demo (67 seconds). The demo runs the real app in a stand-in chat with scripted replies; see demo/.
Mind Map MCP is an MCP App: a server that gives an AI client tools, plus a view the client shows inside the conversation. It is built on the PlugMCP framework, is MIT licensed, and keeps your diagrams on your own computer.
Why
Reading a long answer means holding its structure in your head. A diagram puts the structure on the screen: what belongs together, what follows what, what is missing. See docs/RESEARCH.md for the evidence and the design rules that follow from it.
Other diagram tools for AI have the model place every shape by coordinates. Here the model sends only ideas and how they connect. The app works out the drawing. That is why you can switch the same content between nine structures and six styles with one click and no new request to the AI.
Related MCP server: Flowchart MCP
What you can do
Ask for a diagram. "Break this plan down as a mind map." "Show the sign-up flow as a flowchart." "Why did checkout fail? Use a fishbone."
Switch the structure. Mind map, two sided, logic chart, org chart, outline, timeline, fishbone, flowchart, swimlanes.
Switch the style. Match the chat, classic, minimal, blueprint, sketch, high contrast. Light and dark.
Turn animation on or off. New nodes grow out of their parent and layouts glide into place. It follows your system's reduced motion setting.
Edit on the canvas. Double-click to rename, drag a node onto another to move it, Tab for a child, Enter for a sibling, Delete to remove, Ctrl+Z to undo.
Talk to the AI through the diagram. Select a node and press Explain, Expand, Break down, Challenge or To tasks, ask your own question, or leave comments and send them together. The AI answers by changing the same diagram.
Export. PNG, SVG, a Markdown outline, or the data as JSON.
|
|
|
|
|
|
Every structure in every style: docs/gallery.
Install
The npm package is being published. If
npx mindmap-mcpis not found yet, use From source.
Mind Map runs on your computer with Node 20.19 or newer. Add it to your AI client:
Claude Desktop, in claude_desktop_config.json, and Cursor, in .cursor/mcp.json:
{
"mcpServers": {
"mindmap": { "command": "npx", "args": ["-y", "mindmap-mcp"] }
}
}VS Code, in .vscode/mcp.json:
{
"servers": {
"mindmap": { "command": "npx", "args": ["-y", "mindmap-mcp"] }
}
}Claude Code:
claude mcp add mindmap -- npx -y mindmap-mcpOn Windows, if the client cannot start npx, use "command": "cmd" with "args": ["/c", "npx", "-y", "mindmap-mcp"].
From source
git clone https://github.com/plugmcp-ai/mindmap-mcp.git
cd mindmap-mcp
pnpm install
pnpm buildThen point your client at the built server: "command": "node", "args": ["/full/path/to/mindmap-mcp/bin/mindmap.js"].
Which clients work
Client | Diagram in the chat | Notes |
Claude Desktop | Yes | Inline and full screen. |
Cursor | Yes | |
VS Code (Copilot) | Yes | Inline only. A message from the diagram lands in the message box; press Enter to send it. |
Claude Code and other text-only clients | No | The AI still gets the diagram as an indented outline, and can read and edit it. |
claude.ai on the web, ChatGPT | Needs a hosted server | These accept remote servers only. See below. |
This table comes from each client's documentation. What has been tested on a real client so far, and what has not, is in docs/HOSTS.md.
Hosting it yourself. mindmap-mcp --http serves MCP at http://127.0.0.1:3333/mcp. To accept other computers, set MINDMAP_ALLOWED_HOSTS to the host names you serve and put it behind HTTPS. There is no sign-in: anyone who can reach the address can read and change every diagram, so do not expose it to the internet as it is.
Where your diagrams live
Each diagram is one JSON file in ~/.plugmcp/mindmap/. Set MINDMAP_DIR to keep them somewhere else. Nothing is sent anywhere: the server makes no network calls, and the view loads nothing from outside.
How it works
You ask -> the AI calls visualize -> the diagram appears in the chat
|
you edit, comment or press a node action |
v
the AI is told -> the AI calls edit_diagram -> the same diagram updatesTool | Who calls it | What it does |
| the AI | Makes a diagram from nodes and how they connect, or shows one again. |
| the AI | Changes a diagram that is on screen: add, rename, move, remove, link. |
| the AI | Reads a diagram as an outline, with your comments and what you changed. |
| the view only | Keep the view and the saved file in step. The AI never sees these. |
More in docs/ARCHITECTURE.md.
Contributing
A new style is one file of colors. A new structure is one function that places boxes. Both show up in the toolbar and the gallery, and the tests check them for you. Start with CONTRIBUTING.md.
pnpm install
pnpm dev # the PlugMCP Studio, with a chat to try the tools
pnpm test # unit tests
pnpm test:e2e # the whole loop in a real browser
pnpm gallery # redraw docs/gallery
pnpm demo # re-record docs/demo.mp4 and docs/demo.gif (needs ffmpeg)License
MIT. See LICENSE.
Available Tools
6 toolsedit_diagramChange a diagramA
Change a diagram that is already on screen. Use it after the user edits, comments on or asks about a node, and for any refinement. Do not call visualize again for that. Ops apply in order and address nodes by id. A new node's id can be used by later ops in the same call. The open diagram updates itself.
Inputs: ops (required), docId (required).
exportC
The view writes the diagram to a file on this machine.
Inputs: docId (required), format (required), data.
get_diagramRead a diagramARead-only
Read a diagram as an indented outline with node ids, the user's comments, and what the user changed on the canvas. Use it before editing when you are unsure of the current state, or when the client cannot show the diagram. Without docId it reads the most recent one.
Inputs: docId, sinceRevision.
load_stateCRead-only
The view reads the diagram, or learns it is up to date.
Inputs: docId (required), sinceRevision.
save_stateC
The view saves what the user changed on the canvas.
Inputs: ops (required), docId (required).
visualizeShow a diagramA
Show an idea to the user as a diagram instead of a long text. Pick the structure from what the content is: exploring a topic -> mindmap; a hierarchy or parts of a whole -> org or logic; steps and decisions -> flowchart; causes of a problem -> fishbone; events in order -> timeline; who does what -> swimlanes (give lanes, and a lane on each node); a long list to read top to bottom -> outline. Rules: labels of 1-5 words; 3-7 children per node; at most 3 levels and about 30 nodes at first; put detail in note. Give every node a short id. For a tree set parent on every node but the root. For a flowchart leave parent out and join the nodes with edges; label the edges out of a decision. The first node is the root or the start. Send no positions and no colors. To show a diagram again, pass only its docId. To change one that is on screen, use edit_diagram, not this tool.
Inputs: docId, edges, lanes, nodes, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
visualize (create) and edit_diagram (modify) have clearly separate roles, and get_diagram reads state. The remaining three (load_state, save_state, export) are view-side plumbing whose boundaries are fuzzier — load_state's description ('reads the diagram, or learns it is up to date') is vague and overlaps conceptually with get_diagram.
edit_diagram, get_diagram, load_state, save_state follow a consistent verb_noun pattern, but visualize and export are bare verbs with no noun object, and the noun spelling varies (diagram vs. state). Readable but not uniform.
Six tools is a reasonable scope for a diagram server. However, three of the six (load_state, save_state, export) are client/view plumbing rather than agent-facing capabilities, which makes the set feel slightly padded relative to the core visualize/edit/get trio.
The core lifecycle is covered: create (visualize), read (get_diagram), update (edit_diagram), and export. Missing a delete/remove-diagram operation and any listing of existing diagrams, but these are minor gaps an agent can work around.
Maintenance
Related MCP Connectors
Build and edit real mind maps from a chat: brainstorm, plan, organise notes. Free, never metered.
Draw architecture diagrams, UML, planning boards and clickable wireframes from your AI assistant.
Flowcharts that people and agents edit together on one live canvas, exported as Mermaid.
Create, edit and organize hand-drawn diagrams (flowcharts, ER, architecture) from any AI agent.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceCreate visual whiteboards, diagrams, flowcharts, and project plans from AI conversations. 17 MCP tools for board management, element creation, and real-time collaboration.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to create, edit, and export flowcharts through a local web-based editor with visual drag-and-drop, real-time sync, and 14 MCP tools for full node/edge CRUD.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to generate interactive Excalidraw diagrams with viewport camera control and fullscreen editing directly in the chat.5,690MIT
- AlicenseNot gradedqualityDmaintenanceEnables creating and editing Draw.io diagrams via natural language, supporting shapes, connectors, and multi-line text.2MIT





