Web Reader
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| fetch_urlA | 获取指定URL的网页内容，并转换为Markdown格式。默认使用Jina Reader，失败时自动切换到本地解析 |
| fetch_multiple_urlsC | 批量获取多个URL的网页内容 |
| fetch_url_with_jinaB | 强制使用Jina Reader获取网页内容（适用于复杂网页） |
| fetch_url_localA | 强制使用本地解析器获取网页内容（适用于简单网页或Jina不可用时） |
| fetch_url_with_browserA | 强制使用Playwright浏览器获取网页内容（适用于有访问限制的网站，如Cloudflare保护、验证码等） |
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 5 tools
Each tool has a distinct purpose: batch fetching, default with fallback, local parsing, browser rendering, and Jina-only. Descriptions clearly differentiate when to use each, minimizing confusion.
All tools follow a consistent 'fetch_url' prefix with modifiers for specific strategies (local, browser, jina, multiple). Naming pattern is predictable and uniform.
Five tools cover the core functionality of a web reader without redundancy. The count is well-scoped for the domain.
The tool surface covers all common fetching scenarios: single URL with fallback, forced local, forced browser (for restricted sites), forced Jina (for complex pages), and batch fetching. No obvious gaps for the stated purpose.