Click on "Install 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/)
| Name | Required | Description | Default |
|---|---|---|---|
| filename | No | Optional custom filename | |
| visualization | Yes | The mindmap visualization JSON object |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits of this file-writing operation. It only states the action and destination, but omits critical side effects such as whether existing files are overwritten, whether the directory is auto-created, any permission requirements, or what the tool returns after saving. This is a significant gap for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, tightly written sentence that front-loads the verb, object, and destination. Every word contributes to conveying the essential purpose, with no redundancy or irrelevant detail. It is appropriately concise for a tool of this simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the tool's low complexity, the absence of annotations and output schema increases the burden on the description. It fails to explain the behavior of the optional filename (e.g., default naming, overwrite policy), whether the target directory is created automatically, or the return value/confirmation of the save operation. This incomplete context is insufficient for an agent to invoke the tool with confidence.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes both parameters with 100% coverage: 'filename' as optional custom filename and 'visualization' as the mindmap JSON object. The description adds no additional parameter information beyond the schema, so the baseline score of 3 applies since it neither improves nor detracts from the schema's clarity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool's function with a specific verb ('Save') and resource ('visualization JSON') and states the exact destination path (~/.visualize-chat/visualizations/). It distinguishes itself from the sibling tool push_to_navigate by emphasizing local file storage, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It neither mentions the sibling tool nor explains scenarios where local saving is appropriate or inappropriate. The usage context is only implied by the action itself, with no explicit exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.1export_jsonpush_to_navigateThe 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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Turn outlines and hierarchical notes into interactive mind maps through a hosted remote MCP server.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Asar007/visualize-chat-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
