Skip to main content
Glama
README.md
# adhd-mcp

ADHD-friendly **Cursor** agent kit: on-demand Q&A, concise replies with status footer, context stats via MCP.

## Install

```bash
cd your-project
npx adhd-mcp init
```

Reload MCP in Cursor β†’ **new Agent chat**.

## What `init` writes

| Path | Role |
|------|------|
| `.cursor/rules/adhd.mdc` | Output baseline + Q&A gate + coding ladder |
| `.cursor/skills/adhd-qa/` | Q&A clarification workflow |
| `.cursor/skills/adhd-output/` | Short reply + footer format |
| `.cursor/skills/frontend-design/` | Distinctive UI (anti–AI-slop) |
| `.cursor/skills/web-design-guidelines/` | Vercel Web Interface Guidelines audit |
| `.cursor/mcp.json` | Merges `adhd_mcp` server |
| `adhd/sessions/` | Q&A session logs |

## MCP tools

- `estimate_context` β€” context % (reported or ~heuristic)
- `format_status_footer` β€” `πŸ“Š 理解 X% β”‚ θΏ›εΊ¦ Y% β”‚ ctx ~Z%`
- `check_readiness` β€” block code until understanding β‰₯95%
- `verify_against_requirement` β€” after edits: user wording vs coding ladder
- `qa_session_start` / `qa_session_append` β€” session files

## v1 scope

βœ… Rule + Skills + MCP + init  
❌ GitHub search (v2) · hitl integration

## Dev

```bash
npm install
npm run smoke
npm run local-test
node dist/index.js init --cwd /path/to/project --force --local
```

After publish, users run `npx adhd-mcp init` (uses npm; no `--local`).

## License

MIT

TDQS

A3.7/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: context estimation, footer formatting, readiness check, session creation, and session appending. No two tools could be confused for one another.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (estimate_context, format_status_footer, check_readiness, qa_session_start, qa_session_append). Perfectly predictable.

Tool Count5/5

Five tools is well-scoped for this niche server. Each tool earns its place and covers a specific step in the workflow without redundancy.

Completeness5/5

The surface fully covers the intended domain: context awareness, mandatory formatting, readiness gating, and Q&A session lifecycle. No obvious gaps for the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues