Web & Internet
Search the web through the s.stdlang.com SearXNG instance and return its JSON response for automation or downstream tools.
Call this tool from your code in three languages.
curl -X POST 'http://127.0.0.1:3003/en/api/tools/web-search' \
-H 'Content-Type: application/json' \
-d '{"query":"SearXNG search API","language":"en","categories":"general","engines":"","timeRange":"none","safeSearch":"1","page":1,"maxResults":5}'Send a POST request with your inputs as JSON. File parameters require a separate upload first.
POST http://127.0.0.1:3003/en/api/tools/web-search| Name | Type | Required | Description |
|---|---|---|---|
| query | text | Yes | — |
| language | select | No | — |
| categories | text | No | — |
| engines | text | No | — |
| timeRange | select | No | — |
| safeSearch |
Add this tool to your Model Context Protocol server so AI agents can list and call it.
Add this block to your MCP client configuration:
{
"mcpServers": {
"elysiatools-web-search": {
"name": "web-search",
"description": "Search the web through the s.stdlang.com SearXNG instance and return its JSON response for automation or downstream tools.",
"baseUrl": "http://127.0.0.1:3003/mcp/sse?toolId=web-search",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}After connecting to the SSE endpoint, list the exposed tools:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}Invoke the tool by its id, passing arguments built from its parameters:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "web-search",
"arguments": {
"query": "SearXNG search API",
"language": "en",
"categories": "general",
"engines": "",
"timeRange": "none",
"safeSearch": "1",
"page": 1,
"maxResults": 5
}
}
}Questions or issues? Contact [email protected]
| select |
| No |
| — |
| page | number | No | — |
| maxResults | number | No | — |
JSON result
{
"key": {...},
"metadata": {
"key": "value"
},
"error": "Error message (optional)",
"message": "Notification message (optional)"
}