MindpilotCAUTION
See through your agent's eyes. Visualize legacy code, architect new systems, understand everything.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/abrinsmead/mindpilot-mcp) [](https://www.npmjs.com/package/@mindpilot/mcp) [](https://github.com/abrinsmead/mindpilot-mcp/blob/main/LICENSE)
See through your agent's eyes. Visualize legacy code, inspect complex flows, understand everything.
[!TIP] Mindpilot is now available as a lightweight agent skill—no local MCP server needed. Ask your agent to diagram something and it builds a self-contained, interactive Mermaid viewer you can open in your browser or publish as a Claude artifact. Install with: npx skills add abrinsmead/skills/mermaid-viewerWhy Mindpilot?
- Visualize Anything: Use your coding agent to generate on-demand architecture, code, and process diagrams to view your code from different perspectives.
- Vibe Checks: AI-generated code can accumulate unused and redundant constructs. Use visualizations to spot areas that need cleanup.
- Local Processing: Diagrams are never sent to the cloud. Everything stays between you, your agent, and your agent's LLM provider(s).
- Export & Share: Export any diagram as a vector image.
Prerequisites
Node.js v20.0.0 or higher.
Quickstart
Claude Code
claude mcp add mindpilot -- npx @mindpilot/mcp@latest
Cursor
Under Settings > Cursor Settings > MCP > Click Add new global MCP server and configure mindpilot in the mcpServers object.
{
"mcpServers": {
"mindpilot": {
"command": "npx",
"args": ["@mindpilot/mcp@latest"]
}
}
}VS Code
Follow the instructions here for enabling MCPs in VS Code: https://code.visua
cdb17b1c8876OBSERVED · 2026-10-07Connect
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 client -- npx -y [email protected]
{
"mcpServers": {
"client": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
open_ui | read | Open the Mindpilot UI application |
render_mermaid | read | Render a Mermaid diagram to SVG format. CRITICAL RULES: 1) Node IDs must be alphanumeric without spaces (use A1, nodeA, start_node). 2) For node labels with special characters, wrap in quotes: A[ |
Trust audit
CAUTIONgrade B · trust 85/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| 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
- declared (5 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (10)
.env
.dxtignore
.env
import { cn } from '../../lib/utils';import { cn } from '../../lib/utils';import { cn } from '../../lib/utils';import packageJson from '../../../../package.json';
import type { ElectronAPI } from '../../../electron/preload.js';@fastify/static, @modelcontextprotocol/sdk, fastify, open, posthog-js, @anthropic-ai/dxt, @types/node, @types/ws
@monaco-editor/react, @radix-ui/react-context-menu, @radix-ui/react-dialog, @radix-ui/react-dropdown-menu, @radix-ui/react-icons, @radix-ui/react-select, @radix-ui/react-separator, @radix-ui/react-slo
Gates applied: no_behavioural_pass.
cdb17b1c8876full audit observations/trust-audit/mcp-server/abrinsmead__mindpilot.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 |
|---|---|---|---|---|---|
| 2026-10-07 | cdb17b1c8876 | CAUTION | B | 85 | first audit |
Questions
What is the Mindpilot MCP server?
See through your agent's eyes. Visualize legacy code, architect new systems, understand everything.
What tools does Mindpilot expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Mindpilot safe to connect to an agent?
With care. The audit graded it B (85/100) and found 10 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Mindpilot need?
No credential environment variables were found in its source, so it appears to need none.
How does Mindpilot run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as client at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (cdb17b1c8876), read on 2026-10-07. The repository is watched and re-audited when it changes.