Scan MCP

scan-mcp

Minimal MCP server for scanner capture (ADF/duplex/page-size), batching, and multipage assembly.

Features

• Small, typed MCP server exposing tools for device discovery and scan jobs
• zod-validated inputs; the JSON Schemas in schemas/ document the contract and are contract-tested
• Smart device selection (prefers ADF/duplex, avoids camera backends), robust defaults
• Local-first transports: stdio by default to keep everything on-device, optional HTTP for your own network deployments

Note: This package targets Node 22 and Linux SANE backends (scanimage).

Quick Start (local stdio, default)

Add a server entry to your MCP client configuration:

{

"mcpServers": { "scan": { "command": "npx", "args": [ "-y", "scan-mcp" ], "env": { "INBOX_DIR": "~/Documents/scanned_documents/inbox" } } } }

• This invocation runs over stdio for a privacy-first, single-machine setup.
• Call start_scan_job without a device_id to auto-select a scanner and begin scanning.
• Artifacts are written under INBOX_DIR per job: job-*/page_*.tiff, doc_*.tiff, manifest.json, events.jsonl. When crop_carrier_sheets is set and a carrier sheet is detected, a page_*.cropped.tiff derivative is also written per affected page.

Streamable HTTP transport

Prefer to attach the scanner to another machine on your network? scan-mcp also supports the streamable HTTP transport:

scan-mcp --http

• Default port is 3001; set MCP_HTTP_PORT to override (for example MCP_HTTP_PORT=3333 scan-mcp --http).
• Binds 127.0.0.1 by default. Set MCP_HTTP_HOST to expose it on other interfaces (for example MCP_HTTP_HOST=:: for all, or a LAN address); the server has no authentication, so only do that on a trusted network.
• HTTP responses use server-sent events (SSE) for streaming tool output; clients such as Claude Desktop and Windsurf support this transport.
• There is currently no authentication; widen the bind address only on a trusted internal network.

Install

• Run with npx: npx scan-mcp (recommended)
• The CLI runs a quick preflight check for Node 22+ and required scanner/image tools and prints installation hints if anything is missing.
• See recommended server config above
• Use npx scan-mcp --http to launch the streamable HTTP transport when running on another machine.
• CLI help: scan-mcp --help
• From source (for development):
• npm install
• npm run build
• For Cline setup, and other automated agentic installation, see llms-install.md

System Requirements

• Linux with SANE utilities: scanimage
• TIFF tools: tiffcp (multipage assembly) and ImageMagick convert (carrier-sheet detection and cropping); preflight requires both

Environment Variables

• SCAN_MOCK (default: false): mock SANE calls and generate fake TIFFs for testing.
• INBOX_DIR (default: scanned_documents/inbox): base directory for job runs and artifacts.
• SCANIMAGE_BIN (default: scanimage): override the binary path.
• TIFFCP_BIN / IM_CONVERT_BIN (defaults: tiffcp / convert): multipage assembly and image analysis tools.
• SCAN_EXCLUDE_BACKENDS (CSV): backends to exclude (e.g., v4l).
• SCAN_PREFER_BACKENDS (CSV): preferred backends (e.g., epjitsu,epson2).
• PERSIST_LAST_USED_DEVICE (default: true): persist and lightly prefer last used device.
• LOG_LEVEL (default: info): pino log level.
• MCP_HTTP_PORT (default: 3001): TCP port for the HTTP transport.
• MCP_HTTP_HOST (default: 127.0.0.1): bind address for the HTTP transport.

API

Tools

• list_devices
• Discover connected scanners with backend details.
• Inputs: none.

• get_device_options
• Get SANE options for a specific device.
• Inputs:
• device_id (string): Target device identifier.

• start_scan_job
• Begin a scanning job; omitting device_id triggers auto-selection and default options.
• Inputs (all optional unless noted):
• device_id (string)
• resolution_dpi (integer, 50–1200)
• color_mode (Color | Gray | Lineart): color_mode defaults to Lineart (document-first); at >= 600dpi it defaults to Color, since high-dpi capture usually means artwork/photos where 1-bit destroys information. Pass color_mode explicitly to override either default; high dpi is the only signal used.
• source (Flatbed | ADF | ADF Duplex)
• duplex (boolean)
• page_size (Letter | A4 | Legal | Custom)
• custom_size_mm { width, height }
• doc_break_policy { type (page_count | none), page_count }: split the batch into documents of page_count pages
• output_format (string, default tiff)
• tmp_dir (string)
• crop_carrier_sheets (boolean, default false): detect carrier-sheet leading-edge band and write cropped page derivatives; raw pages are kept

• get_job_status
• Inspect job state and artifact counts.
• Inputs:
• job_id (string)

• cancel_job
• Request job cancellation; best effort during scan loops.
• Inputs:
• job_id (string)

• list_jobs
• List recent jobs from the inbox directory.
• Inputs (optional):
• limit (integer, max 100)
• state (running | completed | cancelled | error | unknown)

• get_manifest
• Fetch a job's manifest.json.
• Inputs:
• job_id (string)

• get_events
• Retrieve a job's events.jsonl log.
• Inputs:
• job_id (string)

See JSON Schemas in schemas/ for input shapes. Runtime validation is zod (src/server/register.ts); the schemas document the contract and tests assert against them.

How Selection and Defaults Work

Defaults aim for 300dpi, reasonable color mode, and ADF/duplex when available. Full details on scoring and fallbacks live in docs:

• Selection and defaults: docs/SELECTION.md

Project Layout

• src/mcp.ts — MCP server entry and tool registration
• src/services/* — hardware interface and job orchestration
• schemas/ — JSON Schemas documenting the tool contracts (used by tests)
• docs/ — architecture, conventions, and deep dives

Development

• npm run dev (stdio MCP server), npm run dev:http (HTTP transport)
• make verify runs lint, typecheck, and tests
• Conventions: docs/CONVENTIONS.md and architecture in docs/BLUEPRINT.md

Roadmap

Tracking ideas and future improvements are documented in docs/ROADMAP.md.