websearch-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEBSEARCH_RESULTS | No | Top N results to fetch full text for (max 12) | 10 |
| WEBSEARCH_USE_CURL | No | Last fallback: plain HTTP fetch | 1 |
| WEBSEARCH_SEARXNG_URL | No | SearXNG endpoint (JSON format auto-appended) | http://100.77.7.3:8890/search |
| WEBSEARCH_BROWSEROS_URL | No | BrowserOS MCP (streamable HTTP) | http://127.0.0.1:9002/mcp |
| WEBSEARCH_USE_BROWSEROS | No | Use BrowserOS batch extraction | 1 |
| WEBSEARCH_MAX_PAGE_CHARS | No | Truncate each page's text to this many chars (context budget) | 8000 |
| WEBSEARCH_USE_PLAYWRIGHT | No | Fall back to headless Chromium | 1 |
| WEBSEARCH_PAGE_TIMEOUT_MS | No | Per-page read/navigation timeout | 25000 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| websearchA | Search the web (SearXNG) and return the full body text of the top N results. Pages are loaded in parallel via BrowserOS, falling back to headless Chromium (Playwright) then plain HTTP fetch. Returns each result as {title, url, text}. |
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
Only one tool exists, so there is no possibility of confusing it with another. The tool's purpose is clearly defined as web search, with a detailed description of behavior.
With a single tool named 'websearch', there is no inconsistency or mixed conventions. The name is descriptive and matches the server's purpose.
The server has only one tool, which is borderline thin. However, for a focused web search server, a single tool can be appropriate, though it lacks the breadth of a multi-tool search suite.
The tool covers the core web search workflow, including fetching top results and body text. Minor gaps may exist such as advanced filtering options, but the essential functionality is present.