Skip to main content
Glama
Asar007

mcp-chat-visualizer

by Asar007
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

mcp-chat-visualizer

An MCP (Model Context Protocol) server that visualizes conversations as structured hierarchical mind maps.

When you call the visualize_chat tool, it injects a mind map generation prompt into the conversation. The LLM then generates a structured JSON mind map of your chat — no API keys or external calls needed.

Installation

npm install -g mcp-chat-visualizer

Or use directly with npx:

npx mcp-chat-visualizer

Related MCP server: CaptureMind

Setup

Add to your MCP client config (Claude Code, Claude Desktop, etc.):

{
  "mcpServers": {
    "chat-visualizer": {
      "command": "npx",
      "args": ["mcp-chat-visualizer"]
    }
  }
}

Claude Code

claude mcp add chat-visualizer -- npx mcp-chat-visualizer

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "chat-visualizer": {
      "command": "npx",
      "args": ["mcp-chat-visualizer"]
    }
  }
}

Usage

Once configured, ask your LLM to visualize the conversation:

"Visualize this conversation as a mind map"

The LLM will call the visualize_chat tool and generate a JSON mind map like:

{
  "metadata": { "topic": "...", "contentType": "mindmap", "nodeCount": 12 },
  "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" },
    { "id": "e2", "source": "cat1", "target": "leaf1", "type": "connects" }
  ],
  "hierarchy": {
    "root": ["cat1"],
    "cat1": ["leaf1"]
  }
}

JSON Schema

Field

Description

metadata

Topic name, content type, total node count

nodes

Array of nodes with id, label, type (root/category/leaf), summary, hoverSummary

edges

Connections between nodes (source → target)

hierarchy

Parent-children mapping matching the edges

Node Types

  • root — Central topic of the conversation

  • category — High-level grouping (4-6 per map)

  • leaf — Specific details, facts, or examples

The mind map goes 3-4 levels deep: Root → Categories → Sub-categories → Leaves.

How It Works

  1. You ask the LLM to visualize the conversation

  2. The LLM calls the visualize_chat tool with the conversation text

  3. The tool returns structured prompt instructions

  4. The LLM follows the instructions and generates the mind map JSON

  5. You get the JSON in the chat, ready to use in your UI

No external API calls. No API keys. The server is a lightweight prompt delivery mechanism — the LLM does all the generation.

License

ISC

Available Tools

1 tool
visualize_chatVisualize ChatA

Visualize a conversation as a hierarchical mind map. Pass the conversation text and receive structured instructions. Follow the returned instructions to generate the mind map JSON.

ParametersJSON Schema
NameRequiredDescriptionDefault
conversationYesThe conversation text or summary to visualize as a mind map

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently reveals that the tool's output is structured instructions, not the actual mind map, and that the user must follow these instructions to produce the JSON. This is a key behavioral trait beyond the schema and is well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first states the core purpose, and the second explains the procedure. It is front-loaded and contains no unnecessary words, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with no output schema, the description covers the entire workflow: input, output (instructions), and required follow-up action. It could specify the instruction format in more detail, but it is sufficiently complete for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage for the single 'conversation' parameter, including a clear description. The tool description adds no additional parameter semantics beyond what the schema already offers, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool visualizes a conversation as a hierarchical mind map, and importantly clarifies that it returns structured instructions rather than the final JSON. This is specific and understandable, though it slightly diverges from the 'visualize' name. There are no sibling tools to differentiate from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear usage flow: pass conversation text, receive instructions, then follow them to generate the mind map JSON. However, it does not explicitly state when to use this tool vs alternatives or any exclusions. Usage is implied rather than directly guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • First observedvisualize_chat
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

With only one tool, there is no possibility of selecting the wrong tool. The tool's purpose is clearly and uniquely described.

Naming Consistency5/5

The single tool 'visualize_chat' follows a clear verb_noun pattern, making its function predictable and consistent.

Tool Count3/5

The server has only one tool, which feels thin on the count scale, though it is appropriately scoped for a very specific visualization purpose.

Completeness5/5

The tool covers the full intended functionality of converting conversation text into mind map instructions, with no obvious missing operations for its narrow domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Mindmap MCP Server

    YuChenSSR
    A
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that converts Markdown content into interactive mindmaps, allowing AI assistants to visualize hierarchical information through either HTML content or saved files.
    1
    236
    MIT

  • fish-bridge-mcp

    MakeaMouse
    A
    license
    A
    quality
    D
    maintenance
    Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.
    9
    2
    MIT

  • mindkeeper-mcp

    icedsg
    A
    license
    A
    quality
    D
    maintenance
    Captures ideas from conversations and organizes them into a persistent, hierarchical mindmap. Supports search, deduplication, export, import, and cloud sync.
    13
    25
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Asar007/mcp-chat-visualizer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server