webclaw
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Ollama URL for local LLM features | http://localhost:11434 |
| WEBCLAW_PROXY | No | Single proxy URL | |
| OPENAI_API_KEY | No | OpenAI API key for LLM features | |
| WEBCLAW_API_KEY | No | Cloud API key (enables bot bypass, JS rendering, search, and research tools) | |
| ANTHROPIC_API_KEY | No | Anthropic API key for LLM features | |
| WEBCLAW_PROXY_FILE | No | Path to proxy pool file |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| batchB | Extract content from multiple URLs concurrently. |
| brandA | Extract brand identity (colors, fonts, logo, favicon) from a website's HTML and CSS. Automatically falls back to the webclaw cloud API when bot protection is detected. |
| crawlB | Crawl a website starting from a seed URL, following links breadth-first up to a configurable depth and page limit. |
| diffA | Compare the current content of a URL against a previous extraction snapshot, showing what changed. Automatically falls back to the webclaw cloud API when bot protection is detected. |
| extractA | Extract structured data from a web page using an LLM. Provide either a JSON schema or a natural language prompt. Automatically falls back to the webclaw cloud API when bot protection is detected. |
| mapA | Discover URLs from a website's sitemaps (robots.txt + sitemap.xml). |
| researchA | Run a deep research investigation on a topic or question. Requires WEBCLAW_API_KEY. Starts an async research job on the webclaw cloud API, then polls until complete. |
| scrapeA | Scrape a single URL and extract its content as markdown, LLM-optimized text, plain text, or full JSON. Automatically falls back to the webclaw cloud API when bot protection or JS rendering is detected. |
| searchB | Search the web for a query and return structured results. Requires WEBCLAW_API_KEY. |
| summarizeA | Summarize the content of a web page using an LLM. Automatically falls back to the webclaw cloud API when bot protection is detected. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Most tools have distinct purposes, but there is some potential overlap between 'extract' (structured data via LLM) and 'scrape' (content extraction in various formats), which could cause confusion. Other tools like 'brand', 'diff', 'map', and 'summarize' are clearly specialized, helping to minimize misselection.
All tool names follow a consistent pattern of single, descriptive verbs (e.g., batch, brand, crawl, diff, extract, map, research, scrape, search, summarize). There are no mixed conventions or deviations, making the set predictable and easy to navigate.
With 10 tools, the count is well-scoped for a web scraping and research server. Each tool appears to serve a specific function in the domain, from basic scraping to advanced research, without feeling excessive or insufficient for the intended purpose.
The toolset covers a broad range of web-related operations, including extraction, crawling, searching, and analysis. Minor gaps exist, such as the lack of explicit update or delete operations for stored data, but these are not critical for the server's primary focus on content retrieval and processing.