Inkra Mcp

Created By
juergenkoller-software14 days ago
Overview

Inkra MCP Server

Swift Platform License MCP juergenkoller-software/inkra-mcp MCP server

Drive a native macOS Markdown editor from Claude, Cursor, or any MCP client.

This is the official Model Context Protocol bridge for Inkra — a native macOS Markdown editor (SwiftUI + AppKit, not Electron) with live KaTeX/Mermaid preview and a built-in AI assistant.

You need the Inkra app installed and running. This MCP server is a stdio→HTTP bridge — Inkra owns the document state, undo stack, syntax highlighting, and rendering. Get Inkra at store.juergenkoller.software/apps/inkra.


What you can do

"Claude, open ~/Notes/2026-thesis.md, find every heading that contains 'TODO', add a checkbox after it, and save."

"Cursor, list all files in the current folder, bookmark the H2 'Methodology', and switch to Focus Mode."

The MCP server exposes 18 tools across these categories:

CategoryTools
Document contentdocument_get_content, document_set_content, document_insert, document_replace, document_search
Document lifecycledocument_open, document_create, document_save
Navigationoutline_get, bookmarks_list, bookmark_add, bookmark_remove
Folder / filesfolder_open, folder_list_files
Metadatafrontmatter_get (YAML front-matter parser)
Viewtheme_set (standard / sepia / night), view_mode_set (focus / wide)
Statewindow_info

Every tool operates on the currently open document in the Inkra app — so AI agents see exactly what you see, edits show up live with syntax highlighting and preview, and undo/redo work in the app's normal undo stack.


Installation

Prerequisites

  1. macOS 14 (Sonoma) or later
  2. Inkra app installed and runningget it here (free during beta, available on Mac App Store and direct download)
  3. Swift 5.9+ (Xcode 15+) if building from source

Build from source

git clone https://github.com/juergenkoller-software/inkra-mcp.git
cd inkra-mcp
swift build -c release
# Binary: .build/release/InkraMCP

Pre-built binary

See Releases.


Configuration

Claude Desktop

{
  "mcpServers": {
    "inkra": {
      "command": "/path/to/InkraMCP",
      "env": {
        "INKRA_PORT": "22300",
        "INKRA_TOKEN": "your-token-here"
      }
    }
  }
}

Get INKRA_TOKEN from Inkra → Settings → API & Integrations.

Claude Code

claude mcp add inkra /path/to/InkraMCP \
  --env INKRA_PORT=22300 \
  --env INKRA_TOKEN=your-token-here

Cursor / other MCP clients

Same pattern — stdio MCP server, two env vars.


How it works

┌────────────────┐  JSON-RPC stdio   ┌────────────────┐  HTTP+Bearer   ┌────────────────┐
│  Claude/Cursor │ ───────────────►  │  InkraMCP      │ ─────────────► │  Inkra.app     │
│  (MCP client)  │ ◄───────────────  │   (this repo)  │ ◄───────────── │  (port 22300)  │
└────────────────┘                   └────────────────┘                └────────────────┘

The bridge forwards JSON-RPC over stdio to Inkra's local HTTP MCP endpoint. The app handles document state (NSTextView with TextKit 2), AST-based syntax highlighting, KaTeX/Mermaid live preview, undo/redo, session restore, and exports.


Environment variables

VariableDefaultDescription
INKRA_PORT22300Port of Inkra's local HTTP server
INKRA_TOKEN(none)Bearer token from Inkra Settings (required)

About Inkra

Inkra is a native macOS Markdown editor — not an Electron app. Highlights:

  • Native — SwiftUI + AppKit, real macOS performance
  • Live preview — KaTeX formulas, Mermaid diagrams, code highlighting rendered in real time via WKWebView
  • Focus mode + wide mode — distraction-free writing
  • Built-in AI assistant — Claude, OpenAI, Ollama, or Inkra KI (dedicated endpoint, no API key needed)
  • Export — HTML and PDF with full layout, formulas, diagrams, code blocks
  • Session restore — folder, file, cursor, scroll position
  • MCP server (this repo) + REST API with Swagger UI
  • 23 EU language localizations
  • Available on Mac App Store + direct download

Get Inkra at store.juergenkoller.software


License

MIT — see LICENSE. Bridge open source; Inkra app is commercial.

Issues & support

Built by Juergen Koller Software GmbH.

Project Info
Created At
14 days ago
Updated At
14 days ago
Author Name
juergenkoller-software
Star
-
Language
-
License
-
Category
Tags

Recommend Servers

View All
Docwand

36 minutes ago
//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

31 minutes ago
Puter Mcp

a day ago