Linkwarden
An MCP Server for Linkwarden
What is Linkwarden?
Linkwarden is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for linkwarden
An MCP Server for Linkwarden
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP Server for Linkwarden
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx linkwardenConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Linkwarden
The Linkwarden MCP Server connects AI assistants to your self-hosted or cloud Linkwarden bookmark manager, enabling programmatic control over your entire link library. It exposes tools for creating, reading, archiving, and deleting links and collections, plus full-text search across saved bookmarks. Developers and researchers use it to build AI-powered workflows that automatically organize, tag, and retrieve saved web content through a conversational interface.
Prerequisites
- A running Linkwarden instance (self-hosted via Docker or cloud at linkwarden.app)
- A Linkwarden API token generated in your account settings
- Docker installed (recommended), or Go 1.21+ for building from source
- An MCP client such as Claude Desktop, Claude Code, or Cursor
Generate a Linkwarden API token
Log into your Linkwarden instance, navigate to Settings > API Keys, and create a new token with the permissions you need (read-only for browsing, read-write for creating and archiving links). Copy the token — you will need it for the server configuration.
Pull the Docker image
The recommended way to run the server is via Docker. Pull the latest image from the GitHub Container Registry.
docker pull ghcr.io/irfansofyana/linkwarden-mcp-server:latestTest the server locally
Run the container interactively to verify it connects to your Linkwarden instance before wiring it into your MCP client.
docker run --rm -i --init \
-e LINKWARDEN_BASE_URL=https://your-linkwarden-instance.com \
-e LINKWARDEN_TOKEN=your-api-token \
ghcr.io/irfansofyana/linkwarden-mcp-server:latestAdd the server to your MCP client configuration
Open your MCP client config file (e.g. claude_desktop_config.json on macOS at ~/Library/Application Support/Claude/) and add the linkwarden server entry shown in the examples below.
Restrict toolsets (optional)
By default all toolsets are enabled. Set the TOOLSETS environment variable to a comma-separated list to limit which capabilities are available. Use READ_ONLY=true to prevent any write operations.
# Enable only search and link reading
docker run --rm -i --init \
-e LINKWARDEN_BASE_URL=https://your-instance.com \
-e LINKWARDEN_TOKEN=your-token \
-e TOOLSETS=search,link \
-e READ_ONLY=true \
ghcr.io/irfansofyana/linkwarden-mcp-server:latestLinkwarden Examples
Client configuration
Add this block to your claude_desktop_config.json under the mcpServers key. Replace the URL and token values with your real Linkwarden credentials.
{
"mcpServers": {
"linkwarden": {
"command": "docker",
"args": [
"run", "--rm", "-i", "--init",
"-e", "LINKWARDEN_BASE_URL=https://your-linkwarden-instance.com",
"-e", "LINKWARDEN_TOKEN=your-api-token-here",
"ghcr.io/irfansofyana/linkwarden-mcp-server:latest"
]
}
}
}Prompts to try
Once connected, use these prompts in your AI client to interact with your Linkwarden bookmarks.
- "Search my Linkwarden bookmarks for anything related to machine learning papers."
- "Create a new collection called 'AI Research' in Linkwarden."
- "List all links in my 'Reading List' collection and summarize what each one is about."
- "Archive the link with ID 42 in Linkwarden."
- "Find all bookmarks tagged 'typescript' and list their titles and URLs."Troubleshooting Linkwarden
Server fails to start with 'connection refused' or authentication error
Verify that LINKWARDEN_BASE_URL points to the correct URL of your Linkwarden instance (include https:// and no trailing slash) and that LINKWARDEN_TOKEN is a valid, non-expired API key generated in Linkwarden's Settings > API Keys page.
Docker container exits immediately with no output
The container requires an interactive stdin to communicate via MCP stdio transport. Always include the -i and --init flags when running the container manually. If using Claude Desktop, the MCP client handles this automatically.
Write operations fail even with a valid token
Check whether READ_ONLY is set to true in your environment, which disables all write operations as a safety measure. Remove that variable or set it to false to re-enable link creation, archiving, and deletion.
Frequently Asked Questions about Linkwarden
What is Linkwarden?
Linkwarden is a Model Context Protocol (MCP) server that mcp server for linkwarden It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Linkwarden?
Follow the installation instructions on the Linkwarden GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Linkwarden?
Linkwarden works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Linkwarden free to use?
Yes, Linkwarden is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Linkwarden Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Linkwarden? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Linkwarden in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Linkwarden?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.