Web Analysis MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level for debugging | info |
| CREEPER_PATH | Yes | The file path to the Creeper crawler installation directory | |
| SUMMARY_API_KEY | Yes | Your DeepSeek API key for content summarization | |
| DOMAIN_BLACKLIST | No | Comma-separated list of domains to exclude from search results | pinterest.com,facebook.com,instagram.com |
| DOMAIN_WHITELIST | No | Comma-separated list of domains to prioritize in search results | github.com,stackoverflow.com |
| FILTER_LLM_MODEL | No | Model name for the LLM used for filtering | glm-4.5-air |
| SEARXNG_BASE_URL | Yes | The base URL of the SearXNG search engine | http://127.0.0.1:8086 |
| FILTER_LLM_API_KEY | No | API key for the LLM used for intelligent filtering | |
| FILTER_LLM_ENABLED | No | Enable LLM-based intelligent filtering for search results | true |
| FILTER_MAX_RESULTS | No | Maximum number of search results to return after filtering | 8 |
| FILTER_LLM_BASE_URL | No | Base URL for the LLM API used for filtering | https://api.deepseek.com |
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 |
|---|---|
| web_searchB | 使用 SearXNG 搜索网络内容，通过 Creeper 爬取网页，并返回经过 LLM 总结的结果。适用于需要获取最新网络信息的场景。 |
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 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly distinct as it is the only one available.
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'web_search' follows a clear verb_noun pattern.
A single tool for a server named 'Web Analysis MCP' feels thin and under-scoped. The tool performs web search and summarization, but the server name suggests broader analysis capabilities (e.g., link analysis, content extraction, performance metrics) that are not covered.
The server's domain appears to be web analysis, but with only a search and summarization tool, there are significant gaps. Missing operations might include analyzing page structure, extracting specific data, checking SEO metrics, or monitoring web changes, making the surface severely incomplete for the implied purpose.