Instapaper
Full featured and capable local Instapaper MCP
claude mcp add --transport stdio hendronf-instapaper-mcp node /absolute/path/to/instapaper-mcp-server/build/index.js \ --env INSTAPAPER_PASSWORD="your_instapaper_password" \ --env INSTAPAPER_USERNAME="your_instapaper_email@example.com" \ --env INSTAPAPER_CONSUMER_KEY="your_consumer_key_here" \ --env INSTAPAPER_CONSUMER_SECRET="your_consumer_secret_here"
How to use
The Instapaper MCP Server exposes a set of actions that let Claude and other MCP clients manage and analyze your Instapaper accounts. You can save new bookmarks, organize them into folders, update read progress, fetch article content in bulk, and retrieve highlights and metadata. The server also supports bulk operations that run in parallel for efficiency, such as moving or archiving multiple bookmarks at once, and it includes data endpoints for listing bookmarks, searching, and accessing article content. When integrated with Claude Desktop, you configure the server as an MCP endpoint and Claude can issue requests like list_bookmarks, create_folder, move_bookmarks_bulk, get_articles_content_bulk, and update_read_progress_bulk to automate reading workflows, research synthesis, and regular maintenance tasks. Use the provided environment variables to authorize with Instapaper and enable secure access to your account.
Once configured, you can perform common tasks such as saving new articles with titles and descriptions, organizing content into folders, retrieving full text for analysis, and generating workflows like weekly reading digests or research syntheses. The example workflows in the README illustrate typical sequences for organizing unread bookmarks, reviewing starred articles, batching archival operations, and synthesizing insights across multiple articles.
How to install
Prerequisites:
- Node.js 18+ installed on your system
- An Instapaper account with API credentials (Consumer Key and Consumer Secret)
- Access to Claude Desktop or another MCP client to connect to the server
Step 1: Install dependencies
# Clone or download this repository
# Navigate to the project root
cd instapaper-mcp-server
# Install dependencies
npm install
Step 2: Create and configure environment variables
# Copy example env file
cp .env.example .env
Edit the .env file to include your Instapaper API credentials and account details:
INSTAPAPER_CONSUMER_KEY=your_consumer_key_here
INSTAPAPER_CONSUMER_SECRET=your_consumer_secret_here
INSTAPAPER_USERNAME=your_instapaper_email@example.com
INSTAPAPER_PASSWORD=your_instapaper_password
Step 3: Build the server
npm run build
Step 4: Run or deploy
- Local development: run the built server file directly using Node
node build/index.js - Production/deployment: use your preferred method to run the Node server (PM2, systemd, Docker, etc.). Ensure environment variables are loaded in the runtime environment.
Additional notes
Tips and common issues:
- Ensure you’ve obtained valid Instapaper API credentials and that they are correctly set in the environment (.env).
- The MCP server expects an absolute path to the built index.js when configuring in Claude Desktop; adjust the path accordingly in your config.
- If you encounter authentication failures, double-check credentials and Instapaper API access permissions.
- For Claude Desktop integration, ensure you restart Claude Desktop after updating the MCP server configuration.
- The environment block in the MCP config allows per-server overrides; use it to provide secure, per-instance credentials.
- When using bulk operations, be mindful of rate limits and API constraints; test with smaller batches before scaling up.
Related MCP Servers
bitbucket
Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
shadcn-ui
MCP server for shadcn/ui component references
advanced-homeassistant
An advanced MCP server for Home Assistant. 🔋 Batteries included.
unity-editor
An MCP server and client for LLMs to interact with Unity Projects
website-publisher
AI Website builder and publisher MCP. Quickly publish and deploy your AI generated code as real website URL. Support html, css, js, python etc.