MCP Web Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_LOG_LEVEL | No | 日志级别 | INFO |
| MCP_HTTP_PROXY | No | HTTP 代理 | |
| MCP_USER_AGENT | No | 自定义 User-Agent | 内置 UA |
| MCP_BING_DOMAIN | No | Bing 检索域名（可设 www.bing.com/cn.bing.com） | www.bing.com |
| MCP_HTTPS_PROXY | No | HTTPS 代理 | |
| MCP_SEARCH_ENGINE | No | 搜索引擎：duckduckgo/bing/baidu | duckduckgo |
| MCP_SEARCH_API_KEY | No | 可选搜索 API Key（预留扩展） | |
| MCP_DEFAULT_TIMEOUT | No | 默认请求超时（秒） | 30 |
| MCP_RATE_LIMIT_HTTP | No | http_request 每分钟调用上限 | 30 |
| MCP_RATE_LIMIT_SEARCH | No | web_search 每分钟调用上限 | 5 |
| MCP_RATE_LIMIT_EXTRACT | No | extract_webpage_content 每分钟调用上限 | 10 |
| MCP_SEARCH_API_ENDPOINT | No | 可选搜索 API Endpoint（预留扩展） | |
| MCP_STDIN_INVALID_INPUT_POLICY | No | 非法 stdin 行处理策略：ignore/warn/strict | warn |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| http_requestD | – |
| fetch_jsonD | – |
| batch_http_requestD | – |
| web_searchD | – |
| web_search_and_extractD | – |
| extract_webpage_contentD | – |
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 6 tools
Several tools have overlapping purposes: http_request and fetch_json both perform HTTP requests, and web_search and web_search_and_extract overlap in functionality. The distinctions between generic request and search/extract operations are unclear without detailed descriptions.
Tool names mix different patterns: some start with verbs (fetch_json, extract_webpage_content), while others are noun phrases (http_request, web_search) or compound verbs (web_search_and_extract). No consistent verb_noun convention is followed.
Six tools is a reasonable number for a web server utility, covering HTTP requests, JSON handling, batch operations, search, and extraction without being excessive or minimal.
The set covers core web operations: making requests, fetching JSON, batch processing, searching, and extracting content. Minor gaps exist, such as no explicit tool for HTML parsing beyond extraction, but the core surface is largely complete.