Distill MCP

Distill MCP

MCP bridge for Distill — let Claude, Cursor, or any MCP client rename files based on AI content analysis. 9 tools for renaming, suggestions (preview), folder watching, history, and rule management. Five AI providers: Claude, OpenAI GPT-4o, Gemini, Ollama (local), Apple Intelligence. Bridge open-source (MIT), Distill app is commercial (pay-per-use, no subscription).

Category
访问服务器

README

Distill MCP Server

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

Let Claude, Cursor, or any MCP client rename files for you — automatically, based on content.

This is the official Model Context Protocol bridge for Distill — a native macOS app that uses AI (Claude, OpenAI, Gemini, Ollama, or Apple Intelligence) to read your files and rename them with descriptive, consistent names. No more IMG_4521.jpg or Scan_003.pdf — get 250401 Invoice Telekom.pdf instead.

You need the Distill app installed and running. This MCP server is a stdio→HTTP bridge — the actual file analysis happens in the app. Get Distill at store.juergenkoller.software/apps/distill.


What you can do

"Claude, look at the 47 PDFs in ~/Downloads, rename them based on content, but show me the suggestions first."

The MCP server exposes 9 tools:

Tool What it does
rename_files Analyze file content with AI and rename with descriptive names
suggest_names Suggest new names without renaming (preview mode)
revert_rename Undo a previous rename
get_rename_history Show the rename history (timestamps, before/after, AI provider used)
watch_folder Add a folder to auto-monitoring (new files get renamed in the background)
app_status Current state, AI provider, credits left, watched folders
set_provider Switch AI provider — Claude, OpenAI GPT-4o, Gemini, Ollama (local), Apple Intelligence
get_rules Show naming rules (date format, casing, categories, custom templates)
set_rules Update naming rules

Distill reads PDFs, images (via OCR), Office documents, emails, HTML, RTF, and media files. It extracts date, category, description, sender, and amounts — then builds filenames using your configurable rules.


Installation

Prerequisites

  1. macOS 14 (Sonoma) or later
  2. Distill app installed and runningget it here (free, pay-per-use credits start at €1.99 / 100 renames)
  3. Swift 5.9+ (Xcode 15+) if building from source

Build from source

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

Pre-built binary

Grab the latest DistillMCP from Releases.


Configuration

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "distill": {
      "command": "/path/to/DistillMCP",
      "env": {
        "DISTILL_PORT": "22200",
        "DISTILL_TOKEN": "your-token-here"
      }
    }
  }
}

Find DISTILL_TOKEN in Distill → Settings → API & MCP.

Claude Code

claude mcp add distill /path/to/DistillMCP \
  --env DISTILL_PORT=22200 \
  --env DISTILL_TOKEN=your-token-here

Cursor / other MCP clients

Same pattern — DistillMCP is a stdio MCP server, configured via the two env vars above.


How it works

┌────────────────┐  JSON-RPC stdio   ┌────────────────┐  HTTP+Bearer   ┌────────────────┐
│  Claude/Cursor │ ───────────────►  │  DistillMCP    │ ─────────────► │  Distill.app   │
│  (MCP client)  │ ◄───────────────  │   (this repo)  │ ◄───────────── │  (port 22200)  │
└────────────────┘                   └────────────────┘                └────────────────┘

The bridge reads JSON-RPC 2.0 requests from stdin, forwards them to Distill's local HTTP server at 127.0.0.1:22200/mcp, and writes responses back to stdout. All AI calls (Claude/OpenAI/Gemini/Ollama/Apple Intelligence), file reading (OCR, PDF extraction, Office parsing), credit tracking, and naming logic happen inside the Distill app.

This split lets the wire format stay open-source (audit it, sandbox it, run it through any MCP runtime) while the heavy lifting stays in the app.


Environment variables

Variable Default Description
DISTILL_PORT 22200 Port of Distill's local HTTP server
DISTILL_TOKEN (none) Bearer token from Distill Settings (required)

Errors and trace logs go to stderr so they don't pollute the JSON-RPC stdout channel.


About Distill

Distill is an AI file manager for macOS that automatically renames files based on content analysis. Highlights:

  • No subscription — free app, pay-per-use credits (100 free / 100 for €1.99 / 400 for €4.99 / 1,000 for €8.99)
  • Five AI providers — Claude, OpenAI GPT-4o, Google Gemini, Ollama (local, no API needed), Apple Intelligence
  • Reads everything — PDFs, images (OCR), Office docs, emails, HTML, RTF, media files
  • Local-only mode with Ollama — nothing leaves your Mac
  • Configurable NameBuilder — date formats, casing, categories, custom templates
  • Folder monitoring — drop files in, get them renamed automatically
  • REST API + Swagger UI — for non-MCP automation
  • MCP server (this repo) — for Claude/AI agents
  • Available on Mac App Store + direct download

Get Distill at store.juergenkoller.software


License

MIT — see LICENSE. Bridge is open source; the Distill app is commercial (free-to-try with pay-per-use credits).

Issues & support

Built by Juergen Koller Software GmbH.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选