What input types are supported?
Five tools cover natural language text, JSON strings, ASCII art, public image URLs or base64 data URIs, and Mermaid diagram source.
@erajasekar
Basic information
MCP server for AI Diagram Maker — generate software engineering diagrams from natural language, code, ASCII diagram, images, or Mermaid. Inline diagram rendering using MCP apps UI and diagram URL in responses. Works with Cursor, Claude Desktop, Claude Code, and any MCP-compatible
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ai-diagram-maker": {
"command": "npx",
"args": [
"-y",
"ai-diagram-maker-mcp@latest"
],
"env": {
"ADM_API_KEY": "<your api key>"
}
}
}
}Generate a software engineering diagram from a natural language description. Use this tool when: the user asks to 'create a diagram', 'show me a flowchart', 'visualise the architecture', uses the keyword 'adm' or 'ai diagram maker', or asks for any visual representation of code, systems, processes or data flows. Supported diagram types: flowchart, sequence, ERD, system architecture, network architecture, UML, mindmap, workflow. Returns a link to view and edit the generated diagram in the browser.
Generate a diagram from a JSON structure. Use this tool when the user wants to visualise JSON data such as API responses, database schemas, dependency trees, configuration files, or any structured data. Pass the raw JSON string as `content`. Returns a link to view and edit the generated diagram in the browser.
Convert an ASCII art diagram into a polished visual diagram. Use this tool when the user has an existing ASCII art representation of a system, flow, or architecture and wants it rendered as a proper diagram. Accepts box-drawing characters, arrow representations (-->, ==>), and plain text layouts. Returns a link to view and edit the generated diagram in the browser.
Convert an image (whiteboard photo, screenshot, hand-drawn sketch) into a clean diagram. Use this tool when the user provides an image URL or base64-encoded image and wants it converted to a proper software engineering diagram. Accepts public image URLs or base64 data URIs (data:image/...;base64,...). Returns a link to view and edit the generated diagram in the browser.
Convert a Mermaid diagram definition into a D2 diagram and return a PNG image. Use this tool when the user has existing Mermaid code (flowchart, sequenceDiagram, erDiagram, etc.) and wants it converted to D2 or rendered as an image. Pass the Mermaid source as content. Returns a link to view and edit the generated diagram in the browser.
It is an MCP server for AI Diagram Maker that generates professional software engineering diagrams from plain English descriptions inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent.
Install via npx (no permanent installation) or use the hosted remote server. Configure your MCP client with the server URL and API key either in request headers (HTTP transport) or as an environment variable (stdio transport). Then ask the AI agent to create a diagram using trigger keywords like "adm ...", "create a diagram of ...", or "show me a flowchart".
Five tools cover natural language text, JSON strings, ASCII art, public image URLs or base64 data URIs, and Mermaid diagram source.
Node.js 18+ and an AI Diagram Maker account with an API key.
It supports stdio (local, default) and HTTP/Streamable HTTP (remote). The hosted instance runs at `https://mcp.aidiagrammaker.com/mcp`; when running locally, use `--transport http`.
For stdio transport, set the `ADM_API_KEY` environment variable. For HTTP transport, pass the API key in the request header as `X-ADM-API-Key` or `Authorization: Bearer <key>`.
Yes, set the environment variable `ADM_DEBUG` to `1`, `true`, or `yes` to log request parameters and API payloads to stderr.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Word search generator, crossword generator, and sudoku generator + solver as a local-first MCP server. 15 deterministic tools: printable PDF puzzle worksheets, themed word banks, and verifiable LLM evals. From the makers

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Comments