Snapmcp

io.github.reeinhardddPublished by GitHub account reeinhardddv2.3.2Updated Oct 24, 2026

Visual capture MCP server: terminal colors, code, diffs, PDFs, GIFs. 13 tools, SSRF on by default.

Overview

AI-generated overview

A local MCP server that renders terminal output, code, diffs, markdown, HTML, browser pages and URLs into styled images, PDFs and GIFs for documentation.

What you can do
Capture terminal output with real detected terminal colors, and code or files as Shiki syntax-highlighted images across many languages and themes, plus visual git diffs with green and red lines. Render markdown, arbitrary HTML snippets and browser pages (full-page or viewport) as images, and turn a URL into a PDF. Batch several captures in one call, build animated GIFs or side-by-side sequences from screenshots, and assemble markdown, HTML or PDF documents with embedded captures. Expose capability hints to MCP clients.
When to use it
Useful when an assistant writes documentation, tutorials or pull-request descriptions and needs pixel-faithful visuals rather than structured snapshots: install-command terminal shots, highlighted config files, migration diffs, before/after UI comparisons. It documents; it does not click or fill pages, so pair it with a browser-automation server for interaction.
Requirements
Runs locally as an npm package (npx snapmcp or global install) over stdio; Node.js 20 or newer, or Bun 1.2 or newer. Needs a Chrome/Chromium binary, either a system install or auto-installed at first setup, configurable via SNAPMCP_CHROME_EXECUTABLE and SNAPMCP_CHROME_PROFILE. Output goes to SNAPMCP_DIR (default ./captures). File capture is deny-all until paths are listed in SNAPMCP_ALLOWED_PATHS.
Before you install
capture_file reads local files, so only paths listed in SNAPMCP_ALLOWED_PATHS are reachable; keep that list narrow. Browser and PDF captures fetch URLs, and SSRF protection is on by default (SNAPMCP_SSRF_PROTECTION) — leaving it disabled lets captures reach private network addresses. Using SNAPMCP_CHROME_PROFILE points captures at a real Chrome profile, which may carry cookies and logged-in sessions. Captures are written to disk in SNAPMCP_DIR.

Installation

In SourceWeft

  1. Open Snapmcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[snapmcp]

The visual documentation MCP server.
Terminal · Code · Browser · Markdown · Diff · HTML · PDF · GIF
For documentation workflows — when structured snapshots aren't enough.

[npm version] [npm downloads] [tests] [stars] [MIT]


Real terminal colors, Shiki-highlighted code, visual diffs, PDFs and GIFs — one MCP server, 13 tools. Renders with your system Chrome, or auto-installs Chromium at first setup. SSRF protection on by default. Built for agents that write documentation, not just drive browsers.

Quick Start

Three steps, under two minutes:

1. Install

bash
npm install -g snapmcp# or run without installing: npx -y snapmcp

2. Add to Claude Code (~/.claude/claude.json)

json
{  "mcpServers": {    "snapmcp": {      "command": "npx",      "args": ["-y", "snapmcp"],      "env": {        "SNAPMCP_DIR": "./captures",        "SNAPMCP_THEME": "nord"      }    }  }}

3. Capture

Ask your agent in natural language:

"Capture a terminal screenshot of git log --oneline -5 and a syntax-highlighted PNG of src/index.ts."

The agent calls capture_terminal and capture_file — images land in ./captures/ with your real terminal theme and the chosen syntax theme applied.

Other clients: OpenCode, VS Code / Cline, Docker

OpenCode (opencode.json):

json
{  "mcpServers": {    "snapmcp": {      "command": "npx",      "args": ["-y", "snapmcp"],      "env": {        "SNAPMCP_DIR": "./captures",        "SNAPMCP_FORMAT": "jpeg",        "SNAPMCP_QUALITY": "95"      }    }  }}

VS Code / Cline / Roo-Cline (settings.json → cline.mcpServers):

json
{  "mcpServers": {    "snapmcp": {      "command": "npx",      "args": ["-y", "snapmcp"],      "env": {        "SNAPMCP_DIR": "./captures",        "SNAPMCP_FORMAT": "jpeg"      }    }  }}

Docker:

bash
docker run -i --rm \  -e SNAPMCP_DIR=/captures \  -e SNAPMCP_THEME=nord \  -v /path/to/output:/captures \  ghcr.io/reeinharddd/snapmcp

What it looks like

CapturePreview
Terminal (real detected colors)[terminal capture]
Code (Shiki syntax)[code capture]
Diff (green/red)[diff capture]

Why snapmcp vs Playwright MCP

Different tools for different jobs. Playwright MCP drives a browser through token-efficient accessibility snapshots; snapmcp renders pixel-faithful images for humans to read. If your agent needs to click, use Playwright. If it needs to show, use snapmcp.

Use casesnapmcpPlaywright MCP
Terminal capture with real colors✅ auto-detects Kitty, Gnome, Alacritty, WezTerm themes❌ no terminal support
Code → syntax-highlighted image✅ Shiki, 50+ languages, 27 themes❌ not its purpose
Git diff → visual red/green image✅ capture_diff❌
URL → PDF document✅ capture_pdf❌
Animated GIF from captures✅ capture_gif (zero-dep gifenc)❌
Markdown → styled document✅ capture_markdown, capture_document❌
Browser page screenshot✅ capture_browser (full-page or viewport)✅
Browser automation (click, fill, navigate)❌ screenshots only✅ accessibility-tree driven, token-efficient — the right tool for this

Most documentation pipelines pair them: Playwright MCP to interact, snapmcp to document.

Tools

ToolDescription
capture_terminalTerminal output with syntax-colored prompts (auto-detects real terminal theme)
capture_codeSyntax-highlighted code via Shiki (50+ languages, 27 themes)
capture_browserFull-page or viewport screenshots (uses system Chrome profile when available)
capture_fileFile → auto-detected language → highlighted screenshot
capture_markdownRendered markdown as a styled document
capture_htmlArbitrary HTML snippet rendered as image
capture_diffGit diffs with green additions / red deletions
capture_pdfURL → PDF document
capture_batchBatch capture multiple items in one call
capture_gifAnimated GIF from multiple screenshots
capture_sequenceSide-by-side animated sequence
capture_documentCreate document (MD/HTML/PDF) with embedded captures
snapmcp-hintServer capability hints for MCP clients

Use cases

Automated documentation — an agent writes a setup guide and embeds real captures: the terminal output of the install command (with your actual theme), the config file syntax-highlighted, the diff of the migration. One prompt, three capture_* calls, images saved next to the markdown.

Visual QA — after a UI change, the agent captures the affected pages with capture_browser, batches before/after with capture_batch, and assembles an animated comparison with capture_gif for the PR description.

Terminal guides — CLI tutorials where the screenshots must match what readers will see: capture_terminal reproduces the real prompt colors instead of a generic dark rectangle.

Security

SSRF protection is on by default — no opt-in required.

FeatureDescription
SSRF ProtectionOn by default (disable with SNAPMCP_SSRF_PROTECTION=false). Blocks IP literals (v4 + v6), localhost variants, and DNS names that resolve to private ranges (127.0.0.0/8, 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, fc00::/7, fe80::/10, etc.); every page request (redirects included) is re-checked
File AllowlistSNAPMCP_ALLOWED_PATHS defaults to deny-all when unset; only explicitly allowed paths can be captured
Path TraversalPrevents ../ escapes, symlink traversal (via realpath), and null byte injection
Input LimitsTerminal 1000 lines; code/markdown/HTML 200KB; diff 500KB; file reads 5MB; max GIF frames 60; max GIF canvas 8192×8192
Audit LogOptional structured JSON log file with timestamped events
Chromium SandboxSandbox availability checked at startup

Configuration

Environment variables for the MCP server:

VariableDefaultDescription
SNAPMCP_DIR./capturesOutput directory for captures
SNAPMCP_THEMEauto-detectedSyntax theme (27 built-in themes + auto-detected terminal)
SNAPMCP_FORMATpngOutput format (png, jpeg)
SNAPMCP_QUALITY90JPEG quality (1-100)
SNAPMCP_PADDING32Content padding in pixels
SNAPMCP_SHADOWnoneDrop shadow (none, soft, medium, strong; aliases sm/md/lg)
SNAPMCP_WINDOW_CHROMEfalsemacOS-style title bar frame
SNAPMCP_BORDER_RADIUS0Window corner radius
SNAPMCP_BADGEfalseFooter badge
SNAPMCP_LOG_FILE—Audit log file path
SNAPMCP_CHROME_EXECUTABLE—Path to Chrome/Chromium binary
SNAPMCP_CHROME_CHANNEL—Chrome channel (stable, beta, dev, canary)
SNAPMCP_CHROME_PROFILE—Chrome profile directory name
SNAPMCP_ALLOWED_PATHS(deny-all)Comma- or semicolon-separated allowed file paths for capture_file

27 built-in Shiki themes: dracula, one-dark-pro, nord, tokyo-night, catppuccin-mocha, catppuccin-latte, ayu-dark, ayu-light, vitesse-dark, vitesse-light, min-dark, min-light, poimandres, rose-pine, rose-pine-moon, rose-pine-dawn, slack-dark, slack-ochin, snazzy-light, github-dark-dimmed, github-light, one-light, solarized-light, solarized-dark, material-theme, material-theme-lighter, material-theme-ocean

CLI

SnapMCP ships with a full CLI beyond the MCP server:

snapmcp        — Start the MCP serversnapmcp init   — Interactive setup wizard (detects Chrome, terminal theme, output dir)snapmcp doctor — Health check: 7 checks across Node, Chromium, paths, envsnapmcp test   — Generate test captures (terminal + code) to verify the setup

Documentation

PageContents
Getting StartedInstallation, quick start, MCP client setup
Tools ReferenceAll 13 tools with parameters and examples
ConfigurationAll SNAPMCP_* env vars, themes, defaults
CLI ReferenceInit, doctor, test commands
GuidesTerminal capture, browser capture, GIF animation
ARCHITECTURE.mdModule map, data flow, security architecture
CONTRIBUTING.mdDev workflow, testing guidelines, PR checklist

Development

bash
git clone https://github.com/reeinharddd/snapmcpcd snapmcpbun installbun run build    # tsc → dist/bun test         # 317 tests

Requirements: Node.js ≥ 20 or Bun ≥ 1.2. CI runs on ubuntu / macOS / windows via GitHub Actions.

License

MIT — see LICENSE.

Source: README.md at commit 9d51c81

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v2.3.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts