linkwarden
An MCP Server for Linkwarden
claude mcp add --transport stdio irfansofyana-linkwarden-mcp-server docker 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 \ --env TOOLSETS="Optional: comma-separated toolsets to enable (e.g., search,collection,link,tags)" \ --env LINKWARDEN_TOKEN="Your Linkwarden API token" \ --env LINKWARDEN_BASE_URL="Your Linkwarden instance URL"
How to use
The linkwarden MCP server provides AI-assisted programmatic access to a Linkwarden instance. It exposes a set of tools for managing bookmark collections, links, and tags, including creating and deleting collections, adding and archiving links, listing tags, and performing advanced searches with pagination. With MCP clients, you can route requests through stdio transport to interact with your Linkwarden data via structured tool calls. You can enable only the toolsets you need (for example, search and collection operations only) and optionally run in read-only mode for safety in production environments.
To use it, configure an MCP client to start the linkwarden MCP server (commonly via Docker, as shown in the examples). Provide the base URL for your Linkwarden instance and a valid API token. You can also pass environment variables or CLI flags to tailor the enabled tools and behavior (such as read-only mode). When running behind Claude or other MCP clients, you’ll typically select tools like get_all_collections, create_link, search_links, or delete_tag_by_id depending on the task, enabling efficient, targeted interactions with your Linkwarden data.
How to install
Prerequisites:
- Access to a Linkwarden instance with a valid API token
- Docker installed on the host (recommended for the quickest setup)
- Optional: Go toolchain if you prefer building from source, or Go install if you want to install the binary directly
A. Using Docker (Recommended)
- Pull and run the MCP server container (adjust URLs and tokens as needed):
docker pull ghcr.io/irfansofyana/linkwarden-mcp-server:latest
docker run --rm -it \
-e LINKWARDEN_BASE_URL=https://your-linkwarden-instance.com \
-e LINKWARDEN_TOKEN=your-api-token-here \
ghcr.io/irfansofyana/linkwarden-mcp-server:latest
- Configure any MCP client to connect via stdio transport to the container, as described in the usage docs.
B. Build from Source
- Clone the repository and build:
git clone https://github.com/irfansofyana/linkwarden-mcp-server.git
cd linkwarden-mcp-server
make build
- Run the binary (ensure Go 1.23+ is installed):
./linkwarden-mcp-server
C. Using Go Install
go install github.com/irfansofyana/linkwarden-mcp-server/cmd/linkwarden-mcp-server@latest
Prerequisites recap:
- Go 1.23 or later if building from source
- Make for building from source
- Docker if using the Docker deployment method
- A reachable Linkwarden instance and a valid API token
Additional notes
Environment variables and config options: You can customize toolsets via TOOLSETS, enable read-only mode with READ_ONLY, and provide the Linkwarden URL and token via base URL/token env vars. When running in production, consider using read-only mode to minimize risk. If you encounter authentication issues, double-check that the token has the required permissions and that the base URL points to the correct Linkwarden instance. If using Docker, ensure the environment variables are correctly passed to the container and that the container has network access to the Linkwarden host. Enable only the tools you need to reduce surface area and improve performance. For debugging, inspect container logs for any startup errors or API request failures.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go