Command-line interface for Linkly AI — search your local documents from the terminal.
The CLI connects to the Linkly AI desktop app's MCP server, giving you fast access to your indexed documents without leaving the terminal.
The Linkly AI desktop app must be running with MCP server enabled. The CLI automatically discovers the app via ~/.linkly/port.
curl -sSL https://updater.linkly.ai/cli/install.sh | shirm https://updater.linkly.ai/cli/install.ps1 | iexbrew tap LinklyAI/tap
brew install linklycargo install linkly-ai-cliPre-built binaries for all platforms are available on the Releases page.
| Platform | File |
|---|---|
| macOS (Apple Silicon) | linkly-aarch64-apple-darwin.tar.gz |
| macOS (Intel) | linkly-x86_64-apple-darwin.tar.gz |
| Linux (x86_64) | linkly-x86_64-unknown-linux-gnu.tar.gz |
| Linux (ARM64) | linkly-aarch64-unknown-linux-gnu.tar.gz |
| Windows (x64) | linkly-x86_64-pc-windows-msvc.zip |
cargo install --path .linkly search "machine learning"
linkly search "API design" --limit 5
linkly search "notes" --type pdf,md,docx| Option | Description |
|---|---|
--limit <N> |
Maximum results (default: 20, max: 50) |
--type <types> |
Filter by document types, comma-separated (e.g. pdf,md,docx,txt,html) |
Get structural outlines for one or more documents (IDs come from search results):
linkly outline <doc-id>
linkly outline <id1> <id2> <id3>linkly grep "pattern" <doc-id>
linkly grep "error|warning" <doc-id> -C 3 -i
linkly grep "TODO" <doc-id> --mode count| Option | Description |
|---|---|
-C, --context |
Lines of context before and after each match |
-B, --before |
Lines of context before each match |
-A, --after |
Lines of context after each match |
-i |
Case-insensitive matching |
--mode |
Output mode: content or count |
--limit |
Maximum matches (default: 20, max: 100) |
linkly read <doc-id>
linkly read <doc-id> --offset 50 --limit 100| Option | Description |
|---|---|
--offset <N> |
Starting line number (1-based) |
--limit <N> |
Number of lines to read (max: 500) |
linkly statusRun as a stdio MCP server for Claude Desktop, Cursor, or other MCP clients:
linkly mcpClaude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"linkly-ai": {
"command": "linkly",
"args": ["mcp"]
}
}
}linkly self-update| Flag | Description |
|---|---|
--endpoint <url> |
Connect to a specific MCP endpoint (e.g. http://192.168.1.100:60606/mcp) |
--json |
Output in JSON format (useful for scripting) |
-V, --version |
Print version |
-h, --help |
Print help |
# Search across LAN
linkly search "budget report" --endpoint http://192.168.1.100:60606/mcp
# JSON output for scripting
linkly search "TODO" --json | jq '.content'
# Pipe document content
linkly read abc123 --limit 50 | head -20Apache-2.0