MCP Web Engine
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEARXNG_URL | No | Operator-controlled SearXNG endpoint with JSON enabled. Required for searches, not initialization. | http://127.0.0.1:8082/search |
| ALLOW_DDG_FALLBACK | No | Enable direct DuckDuckGo fallback with true. | false |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Performs aggregate multi-engine web search returning structured search results. |
| fetch_urlB | Fetches raw text content of a web page after SSRF security checks. |
| extract_markdownB | Scrapes a web page and converts HTML into clean, structured Markdown for LLMs. |
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 3 tools
web_search is clearly distinct, but fetch_url and extract_markdown both retrieve page content and could be confused when an agent wants Markdown versus raw text. The descriptions help differentiate, but the boundary is not as sharp as ideal.
All names use snake_case consistently. However, web_search uses a noun-first pattern while fetch_url and extract_markdown follow verb_noun, creating a minor inconsistency.
Three tools is a tight, well-scoped set for a web engine, covering search, raw fetch, and Markdown extraction without redundancy or bloat.
The core lifecycle (search, fetch, extract) is covered. Minor gaps like batch fetching or metadata extraction exist but are not essential for the stated purpose.