A powerful metasearch CLI that enables AI agents to query multiple search engines in parallel without requiring API keys.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install webserp
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 webserp 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 webserp?
webserp is a specialized metasearch tool designed for AI agents and developers who need real-time web access. By querying seven major search engines simultaneously—including Google, DuckDuckGo, and Brave—it bypasses the limitations of static training data. It utilizes curl_cffi to mimic real browser fingerprints, ensuring high reliability and preventing bot detection without the need for complex API configurations. This makes it an essential component for any workflow involving Openclaw Skills that requires live data.
webserp Use Cases
- Retrieving real-time news and recent events missing from LLM training sets.
- Verifying facts or finding primary sources across multiple search engines.
- Discovering technical documentation, code repositories, and software releases.
- Monitoring search engine results for specific queries across different providers.
How webserp Works
- The user or agent triggers a search query via the CLI.
- webserp initiates parallel requests to up to 7 search engines simultaneously.
- Browser impersonation logic via curl_cffi handles fingerprints to prevent blocks.
- Results are aggregated, deduplicated by URL, and formatted into a structured JSON response.
- The agent parses the SearXNG-compatible JSON to extract relevant links and content snippets.
webserp Setup
Install the package via pip:
pip install webserp
Run a basic search to verify installation:
webserp "latest news on Openclaw Skills"
webserp Data Schema & Taxonomy
The output is returned as a SearXNG-compatible JSON object containing the following structure:
| Field | Type | Description |
|---|---|---|
| query | String | The original search term processed. |
| number_of_results | Integer | Total count of unique results returned. |
| results | Array | Objects containing title, url, content, and engine. |
| unresponsive_engines | Array | List of engines that failed to respond with error reasons. |
| suggestions | Array | Suggested related search terms. |
webserp Advanced Features
- Parallel execution across 7 engines for maximum speed and coverage.
- Integrated URL deduplication to ensure unique search results.
- Support for custom proxies (SOCKS5/HTTP) to rotate IPs and avoid rate limits.
- Selective engine filtering and configurable timeouts for low-latency requirements.
- Full browser impersonation for high-success rate scraping without API keys.
SKILL.md
Loading
Related Openclaw Skills
semfind
A command-line tool for semantic search that finds files based on meaning and concepts rather than exact keyword matches.
A2A Vault (PassBox)
A zero-knowledge secrets manager designed for secure credential storage and automated injection within Openclaw Skills environments.
A2A Marketplace
An AI tool marketplace via AgentForge for discovering, comparing, and executing specialized AI functions with integrated billing.
Windfall Inference
A sustainable LLM inference gateway that routes requests to the cheapest and greenest energy sources with onchain verification.
Confidence Scoring Gatekeeper
A mandatory data integrity gatekeeper that validates and enforces confidence scoring rules before writing entity links to production databases.
Data-Normalization (Artledger)
A specialized data integrity skill that standardizes raw records from multiple sources to ensure accurate identity resolution and enrichment.
Featured*
