WhimsicalSAFE
MCP server for creating whimsical boards from an LLM context
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Whimsical now has an official MCP server available here
A third-party Model Context Protocol (MCP) server that enables the creation of Whimsical diagrams agentically. This server integrates with Whimsical's API to generate diagrams from Mermaid markup.
Demo
Here's an example of a complex system architecture diagram created using this MCP server and Claude - it shows the Model Context Protocol (MCP) architecture itself:
Features
- Create Whimsical diagrams using Mermaid markup generated by the MCP Client (Claude, Windsurf, etc.)
- Returns both the Whimsical diagram URL and a base64 encoded image to allow the Client to iterate on it's original markup
Installation
Installing via Smithery
To install Whimsical MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install BrockReece/whimsical-mcp-server --client claude
Manual Installation
# Clone the repository git clone https://github.com/BrockReece/whimsical-mcp-server.git # Install dependencies yarn install # Build the project yarn build
Integration with MCP Client
Update the MCP Client's config to point to this repository's dist folder eg:
{
"mcpServers": {
"whimsical": {
"command": "node",
"args": [
"/path/to/this/repo/whimsical-mcp-server/dist/index.js"
]
}
}
}License
This project is licensed under the MIT License.
f7866599ab38OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add whimsical-mcp-server -- npx -y [email protected]
{
"mcpServers": {
"whimsical-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
create_whimsical_diagram | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, @playwright/test, @types/node, node-fetch, ts-node, typescript
Gates applied: no_behavioural_pass, no_license.
f7866599ab38full audit observations/trust-audit/mcp-server/brockreece__whimsical.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | f7866599ab38 | SAFE | B | 89 | first audit |
Questions
What is the Whimsical MCP server?
MCP server for creating whimsical boards from an LLM context
What tools does Whimsical expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Whimsical safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Whimsical need?
No credential environment variables were found in its source, so it appears to need none.
How does Whimsical run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as whimsical-mcp-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (f7866599ab38), read on 2026-10-08. The repository is watched and re-audited when it changes.