Markview

Created By
paulhkang943 months ago
MarkView is a native macOS markdown previewer (Swift, ~25MB, no Electron) with an MCP server. Two tools: - `open_file(path)` — open a .md file in MarkView - `preview_markdown(content)` — render markdown content without saving Supports GitHub Flavored Markdown, Mermaid diagrams, syntax highlighting for 18 languages, Quick Look Finder integration, bidirectional scroll sync, and PDF/HTML export. Notarized and Gatekeeper approved. MIT licensed.
Overview

Title:

I built MarkView — an MCP server that lets Claude Code preview rendered markdown in a native window as it writes


Body: I built MarkView to solve a workflow problem: Claude writes a README, RFC, or doc — and I'm staring at raw source. No preview, no rendering, no way to see if the tables look right or the code blocks format correctly until I open another tool.

MarkView is a native macOS markdown previewer (Swift, ~25MB, no Electron) with an MCP server built in. Claude Code gets two tools:

  • open_file(path) — open an existing .md file in MarkView
  • preview_markdown(content) — render markdown content on the fly without saving

When Claude writes docs, you see them rendered in real time in a native window.

Setup for Claude Code — add to ~/.claude/settings.json:

{
  "mcpServers": {
    "markview": {
      "command": "npx",
      "args": ["mcp-server-markview"]
    }
  }
}

That's it. No config, no API keys, runs locally.

What the app does (works standalone too, no Claude required):

  • Live split-pane editor + preview with scroll sync
  • GitHub Flavored Markdown (tables, task lists, strikethrough)
  • Syntax highlighting for 18 languages via Prism.js
  • Mermaid diagrams (flowcharts, sequence, Gantt)
  • Markdown linting with auto-fix on save
  • Quick Look integration — spacebar preview in Finder
  • Export to HTML and PDF
  • Dark mode, 18 settings, notarized

Install:

brew install --cask paulhkang94/markview/markview

MIT licensed. No telemetry. Runs on macOS 14+.

GitHub: https://github.com/paulhkang94/markview MCP registry: https://registry.modelcontextprotocol.io (search "markview")

Happy to answer questions about the MCP setup or the app itself.

Server Config

{
  "mcpServers": {
    "markview": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-markview"
      ]
    }
  }
}
Project Info
Created At
3 months ago
Updated At
2 months ago
Author Name
paulhkang94
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

16 hours ago