# agent-draw MCP Server

> agent-draw MCP Server — nicolaerusan-agent-draw. Use this tool when you need to manage and collaborate on versioned diagram documents, such as reading, importing, and proposing connections for agent-draw diagrams. It solves problems of document version control and real-time collaboration by allowing agents to apply optimistic patches. The server accepts diagram documents as input and outputs updated versions, making it ideal for use cases that require iterative and concurrent editing.

Canonical page: https://skillsregistry.net/skills/nicolaerusan-agent-draw  
JSON: https://api.skillsregistry.net/v1/skills/nicolaerusan-agent-draw

## Description

A TypeScript stdio MCP server that lets agents read, import, propose connections for, and apply optimistic patches to versioned agent-draw diagram documents.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/t8mj4vzlx5)
- **Repository:** <https://github.com/nicolaerusan/agent-draw>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "nicolaerusan-agent-draw"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nicolaerusan-agent-draw` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nicolaerusan-agent-draw/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt