mcp_searxng
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEARXNG_URL | No | SearXNG instance URL | http://localhost:8080/searxng |
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 |
|---|---|
| search_webB | Search the web via SearXNG. Optional: filter by engines, categories (general/news/images/science/files/social+media/videos). |
| search_newsC | Search news articles via SearXNG. |
| search_imagesA | Search images via SearXNG. Returns title, URL, thumbnail, and source. |
| list_enginesA | List all available search engines from the SearXNG instance. Args: enabled_only: If True (default), return only enabled engines. |
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 4 tools
search_news and search_images are clearly distinct from search_web, but search_web can also filter by news/images categories, creating some overlap. The dedicated tools return specialized results, so the intent is mostly clear.
All tools use snake_case with a consistent verb_noun pattern (search_web, search_news, search_images, list_engines). The naming is predictable and uniform.
Four tools is well-scoped for a search server: general search, two specialized searches, and a utility for listing engines. Each tool earns its place without bloat.
Core search and engine listing are covered, but only news and images have dedicated specialized searches. Other categories (videos, science, etc.) are accessible via search_web, so no critical gaps exist, but dedicated support for all categories would be more complete.