Borrowing it
Nothing to install: this file belongs to jacksenechal/scan-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jacksenechal/scan-mcp/main/.claude/skills/setup-mcp/SKILL.mdgit clone --depth 1 https://github.com/jacksenechal/scan-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jacksenechal/scan-mcp/setup-mcp)<a href="https://agentmods.dev/skills/jacksenechal/scan-mcp/setup-mcp"><img src="https://agentmods.dev/badge/skills/jacksenechal/scan-mcp/setup-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jacksenechal/scan-mcp/setup-mcp"><img src="https://agentmods.dev/badge/skills/jacksenechal/scan-mcp/setup-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.00756 |
| Opus 5.5 | $0.00030 | $0.00302 |
| Sonnet 5.5 | $0.00015 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
setup-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scan-mcp MCP Server Setup
Configure the scan-mcp MCP server in Claude Code's global configuration to enable scanner control.
Setup Workflow
Step 1: Gather User Preferences
Ask user for:
- INBOX_DIR location (default:
~/Documents/scanned_documents/inbox) - Installation method: npx (recommended) or local
Step 2: Run Preflight Checks
npx -y scan-mcp --preflight-only
Expected on success: All checks passed!
If preflight fails: Parse output to identify missing dependencies, then guide user through installation (see PLATFORMS.md).
Common missing items:
- SANE utilities (
scanimage,scanadf) - TIFF tools (
tiffcpor ImageMagickconvert)
Step 3: Locate Claude Code MCP Configuration
Claude Code config location:
~/.config/claude/config.json(Linux/macOS)- Create if doesn't exist
Step 4: Add or Update Configuration
Configuration structure (npx - recommended):
{
"mcpServers": {
"scan": {
"command": "npx",
"args": ["-y", "scan-mcp"],
"env": {
"INBOX_DIR": "~/Documents/scanned_documents/inbox"
}
}
}
}
Important:
- If config.json doesn't exist: Create it with scan-mcp server entry
- If config.json exists but no mcpServers: Add mcpServers section
- If mcpServers exists: Add or update "scan" entry
- Preserve existing MCP server configurations
For local installation (advanced): See ADVANCED.md.
Step 5: Verify Configuration
- Inform user that Claude Code needs restart to pick up new configuration
- Suggest testing:
claude mcpor asking "scan this document" - If issues occur, suggest running
/doctor
Quick Example
User: "Setup scan-mcp"
Actions:
- Ask: "Where would you like scanned documents stored? (Default: ~/Documents/scanned_documents/inbox)"
- Run:
npx -y scan-mcp --preflight-only - If preflight passes:
- Locate/create
~/.config/claude/config.json - Add scan-mcp server configuration
- Confirm: "scan-mcp configured. Please restart Claude Code. Test with 'scan this document'."
- Locate/create
- If preflight fails:
- Identify missing dependencies
- Provide installation commands (see PLATFORMS.md)
- Re-run preflight after user installs
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 91 lines · 75 tokens per session scan A ff3b3667d226
setup-mcp is a skill published in the GitHub repository jacksenechal/scan-mcp (6 stars, last pushed 13d ago), licensed MIT. It adds 75 tokens to every session and 756 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
setup-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-mcpjacksenechal/scan-mcp | Skill | 6 | 13d ago | MIT | A | 75 | Claude Code |
| pdf-summarizerTencent/AI-Infra-Guard | Skill | 7.4k | 4d ago | Apache-2.0 | A | 21 | Claude Code, Codex |
| document-queryagent0ai/agent-zero | Skill | 20k | yesterday | none | A | 23 | Claude Code, Codex |
| pdf-readeralibaba/anolisa | Skill | 603 | 2mo ago | Apache-2.0 | A | 19 | Claude Code, Codex |
| docx-presskdcube/kdcube | Skill | 27 | 2d ago | MIT | A | 73 | Claude Code |
| youtube-transcribe-yt-dlpsupermaciz/sessions-chronicle | Skill | 5 | yesterday | MIT | A | 38 | Claude Code, Codex |
| readmd-style-customNatsummerance/readMD | Skill | 25 | 1mo ago | MIT | A | 19 | Claude Code, Codex |