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., "@visualize-chat-mcp visualize this conversation"
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.
MCP server that visualizes Claude conversations as mindmaps.
Works with Claude Desktop, Claude Web, and Claude Code CLI.
npm install -g visualize-chat-mcpRelated MCP server: Supermemory MCP
Add to config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"visualize-chat": {
"command": "npx",
"args": ["-y", "visualize-chat-mcp"]
}
}
}Add to ~/.claude.json:
{
"mcpServers": {
"visualize-chat": {
"command": "npx",
"args": ["-y", "visualize-chat-mcp"]
}
}
}Type /visualize in any Claude conversation.
Claude will:
Read the entire conversation
Generate a mindmap JSON
Save it to ~/.visualize-chat/visualizations/
Tool | Description |
| Save mindmap to local file |
| Upload to Navigate Chat (requires API config) |
To push visualizations to Navigate Chat, add env vars:
{
"mcpServers": {
"visualize-chat": {
"command": "npx",
"args": ["-y", "visualize-chat-mcp"],
"env": {
"NAVIGATE_CHAT_API_URL": "http://localhost:8000",
"NAVIGATE_CHAT_EMAIL": "your-email",
"NAVIGATE_CHAT_PASSWORD": "your-password"
}
}
}
}{
"metadata": { "topic": "...", "contentType": "mindmap", "nodeCount": 15 },
"nodes": [
{ "id": "root", "data": { "label": "Main Topic", "type": "root", "summary": "...", "hoverSummary": "..." } },
{ "id": "cat1", "data": { "label": "Category", "type": "category", "summary": "...", "hoverSummary": "..." } },
{ "id": "leaf1", "data": { "label": "Detail", "type": "leaf", "summary": "...", "hoverSummary": "..." } }
],
"edges": [
{ "id": "e1", "source": "root", "target": "cat1", "type": "connects" }
],
"hierarchy": {
"root": ["cat1", "cat2"],
"cat1": ["leaf1", "leaf2"]
}
}MIT
Save visualization JSON to local file (~/.visualize-chat/visualizations/)
Inputs: visualization (required), filename.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: one saves visualization JSON to a local file, the other pushes it to an API. There is no overlap in their primary functions, so an agent can easily choose the correct one based on the desired destination.
Both tool names use snake_case and start with imperative verbs (export, push). The pattern differs slightly—'export_json' is verb + object, while 'push_to_navigate' includes a preposition—but they remain readable and follow a similar style.
With only two tools, the set feels thin for a general visualization server. However, for the narrow scope of exporting and pushing visualizations, the count is borderline acceptable rather than clearly insufficient.
The tools cover the two primary output paths (local save and remote API push), which covers the core workflow. Minor gaps exist, such as no listing or deletion of saved visualizations, but these are not dead ends for the main use case.
Turn outlines and hierarchical notes into interactive mind maps through a hosted remote MCP server.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
