A real-time internet search skill for AI agents utilizing the Zhipu AI GLM MCP server to retrieve up-to-date web information.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install glm-web-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 glm-web-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 GLM Web Search?
The GLM Web Search skill provides AI agents with the capability to perform live web queries through the Zhipu AI GLM Model Context Protocol (MCP) server. This integration allows agents to bypass training data cutoffs and access the latest news, technical documentation, and online resources in real-time. By leveraging this within the Openclaw Skills ecosystem, developers can build agents that provide factually grounded and current information to users.
GLM Web Search Use Cases
- Fetching the latest news updates and current events for real-time reporting.
- Performing technical research on recently released software, libraries, or APIs.
- Fact-checking user queries against live web sources for improved accuracy.
- Gathering comprehensive summaries, URLs, and site metadata for research-heavy tasks.
How GLM Web Search Works
- The AI agent identifies a request that requires live information or external verification.
- The skill verifies the availability of mcporter and the local GLM API configuration.
- A connection is established to the GLM MCP server via a secure SSE or HTTP endpoint.
- The agent executes the webSearchPrime tool, passing the search query as a parameter.
- The skill retrieves structured results, including page titles, snippets, and source URLs, to enrich the agent's context.
GLM Web Search Setup
To get started, ensure mcporter is functional by running npx -y mcporter --version. Then, obtain an API key from Zhipu AI (bigmodel.cn) and configure it locally:
mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/glm.json << EOF
{
"api_key": "YOUR_GLM_API_KEY"
}
EOF
Register the MCP server using mcporter:
mcporter config add glm-search \
--type sse \
--url "https://open.bigmodel.cn/api/mcp/web_search_prime/sse?Authorization=YOUR_GLM_API_KEY"
GLM Web Search Data Schema & Taxonomy
The skill utilizes a structured configuration file and returns detailed search metadata for the agent to process.
| Component | Detail |
|---|---|
| Configuration File | ~/.openclaw/config/glm.json |
| Primary Tool | webSearchPrime |
| Output Fields | title, url, summary, site_name, site_icon |
| Connection Type | SSE (Server-Sent Events) or HTTP |
GLM Web Search Advanced Features
- Low-latency search result streaming via Server-Sent Events (SSE) support.
- Comprehensive metadata extraction including website icons and source names for high-quality references.
- Centralized MCP management through mcporter for consistent Openclaw Skills performance.
- Secure authentication handling using standard Bearer Token headers.
SKILL.md
Loading
Related Openclaw Skills
Draw.io Diagram Generator
A versatile skill that enables AI agents to transform text-based code into interactive, editable draw.io diagrams.
Book Writer
A professional-grade engineering assistant for the entire novel writing lifecycle, ensuring logical consistency and character stability.
Meal Suggester
An intelligent meal planning and inventory tracking agent that suggests 25-minute recipes based on household preferences and current stock.
Evenrealities Order Tracker
An automated monitoring tool that tracks Evenrealities order statuses using browser automation and provides change-only notifications.
AgentPuzzles
A competitive puzzle arena for AI agents featuring timed challenges, multi-category leaderboards, and automated performance benchmarking.
IDE Agent Kit
A local-first filesystem message bus and webhook relay that enables seamless real-time coordination between multiple AI coding agents.
METADATA
Featured*
