An agentic web search and retrieval skill that enables AI agents to find, scrape, and synthesize real-time internet data through the Linkup API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install linkup-search
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install linkup-search using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Linkup Search?
Linkup Search is a sophisticated tool designed for agentic web retrieval, allowing AI coding agents to move beyond static training data. It functions as a bridge to the live web, interpreting natural language instructions to perform everything from simple keyword lookups to complex, multi-step research missions. By integrating this skill with Openclaw Skills, developers can equip their agents with the ability to reason about query construction, choose between depth-first or breadth-first searches, and extract clean data from dynamic websites.
The skill emphasizes cost-efficiency and technical precision, distinguishing between standard searches for snippets and deep searches for iterative, context-aware scraping. It is an essential component for any workflow requiring up-to-the-minute information, competitive intelligence, or automated data enrichment.
Linkup Search Use Cases
- Conducting deep research by finding URLs and automatically scraping their content for synthesis.
- Extracting specific business data such as pricing tiers, feature lists, or contact info from corporate websites.
- Monitoring real-time news, funding rounds, and market trends with precision date filtering.
- Automating lead enrichment by extracting profile details and recent activity from LinkedIn.
- Powering Q&A chatbots with sourced, verifiable answers gathered from multiple web sources.
How Linkup Search Works
- The agent analyzes existing inputs (URLs vs. keywords) to determine if it should perform a search or a direct fetch.
- It identifies the data's location—whether in search snippets or deep within full web pages—to select the appropriate search depth.
- A query is constructed using either keyword-style for simple facts or instruction-style for complex extractions.
- The agent executes the Linkup tool, choosing between standard (parallel) or deep (sequential) processing based on the complexity of the task.
- Results are returned in the requested format—raw sources, natural language answers, or structured JSON—for the agent to process or display.
Linkup Search Setup
To get started with Linkup using Openclaw Skills, configure your MCP server with your API key. For Claude Code, use the following command:
claude mcp add --transport http linkup https://mcp.linkup.so/mcp?apiKey=YOUR_API_KEY
For VS Code or Cursor, add this entry to your MCP configuration file:
{
"servers": {
"linkup": {
"url": "https://mcp.linkup.so/mcp?apiKey=YOUR_API_KEY",
"type": "http"
}
}
}
Linkup Search Data Schema & Taxonomy
The skill supports three primary output modes to organize data effectively:
| Output Type | Data Structure | Ideal Usage |
|---|---|---|
| searchResults | Array of Objects | Raw data retrieval including name, URL, and content for agent reasoning. |
| sourcedAnswer | String + Sources | Direct answers to user queries with cited references for transparency. |
| structured | JSON Schema | Validated data extraction for CRM updates or programmatic pipelines. |
Additionally, the /fetch endpoint provides raw markdown content from specific URLs with optional JavaScript rendering.
Linkup Search Advanced Features
- Deep Search Mode: Executes up to 10 iterative passes where each step is aware of prior findings.
- LinkedIn Integration: Specialized logic for extracting profile details, comments, and post history.
- Sequential Chaining: Ability to find a URL via search and immediately scrape it in a single tool call.
- Smart Filtering: Precise control over results using domain inclusion/exclusion and specific date windows.
- JavaScript Rendering: The renderJs toggle ensures data can be extracted even from heavy client-side rendered applications.
SKILL.md
Loading
Related Openclaw Skills
Academic Literature Search Skill
A professional-grade academic research tool that integrates multiple authoritative databases for comprehensive, high-speed literature retrieval and analysis.
Link Building Outreach
A sophisticated automation pipeline designed to scale personalized link-building outreach without sacrificing quality.
Tavily Search Skill
A high-performance web search skill using the Tavily API to provide AI agents with real-time, filtered internet access and source discovery.
DiskWatch Disk Space Monitor & Alert
DiskWatch is an automated disk monitoring utility that tracks drive usage, alerts users before capacity is reached, and identifies large files for cleanup.
Deep Research with MCP
A professional-grade research agent skill that utilizes Model Context Protocol (MCP) tools to perform deep web analysis and generate cited technical reports.
Threads Downloader
An automated AI agent skill designed to parse Threads links and download high-definition video content directly to your local storage.
Featured*
