The Mcp Searxng server integrates the SearXNG metasearch API to provide AI assistants with web search and content extraction capabilities. It offers tools for executing paginated web searches with filters for time range, language, and safe search levels, as well as a URL content reader that extracts and caches page content with TTL optimization. This server enables AI assistants to access current web information and retrieve detailed content from URLs by connecting to any SearXNG instance via HTTP JSON API.
claude mcp add mcp-searxng --env SEARXNG_URL=YOUR_SEARXNG_URL -- npx -y mcp-searxngRun in your terminal. Replace YOUR_* placeholders with real values; add --scope user to install for every project.
Review the command, arguments, and environment values before installing — MCP servers run with your local permissions.
Verified live against the running server on Jun 10, 2026.
searxng_web_searchSearches the web using SearXNG and returns a list of results, each with a title, URL, and content snippet. CRITICAL: The required parameter name is exactly `query` (not `prompt`, `q`, or any other name). Calls an external SearXNG instance; availability depends on the `SEARXNG_...6 paramsSearches the web using SearXNG and returns a list of results, each with a title, URL, and content snippet. CRITICAL: The required parameter name is exactly `query` (not `prompt`, `q`, or any other name). Calls an external SearXNG instance; availability depends on the `SEARXNG_...
query*stringpagenonumberlanguagestringmin_scorenumbersafesearchnumber0 · 1 · 2default: 0time_rangestringday · week · month · yearweb_url_readFetches a URL and returns its text content converted to markdown. Three modes: (1) Full content — omit filtering params; use `startChar`/`maxLength` to paginate large pages. (2) Section extraction — set `section` to return content under a specific heading. (3) Headings only —...6 paramsFetches a URL and returns its text content converted to markdown. Three modes: (1) Full content — omit filtering params; use `startChar`/`maxLength` to paginate large pages. (2) Section extraction — set `section` to return content under a specific heading. (3) Headings only —...
url*stringsectionstringmaxLengthnumberstartCharnumberreadHeadingsbooleanparagraphRangestringPrivate web search for AI assistants — connect any SearXNG instance to Claude, Cursor, and more.
An MCP server that integrates the SearXNG API, giving AI assistants web search capabilities.
✨ Featured in the GitHub MCP Registry.
Add to your MCP client configuration (e.g. claude_desktop_config.json):
{
"mcpServers": {
"searxng": {
"command": "npx",
"args": ["-y", "mcp-searxng"],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Replace YOUR_SEARXNG_INSTANCE_URL with the URL of your SearXNG instance (e.g. https://searxng.example.com).
response_format./autocompleter endpoint./config.min_score.| Brave MCP | Exa MCP | Firecrawl MCP | mcp-searxng | |
|---|---|---|---|---|
| Web Search | ✓ | ✓ | ✓ | ✓ |
| Read URL | ✗ | ✓ | ✓ | ✓ |
| Pagination | ✗ | ✗ | ✓ | ✓ |
| Self-hosted | ✗ | ✗ | Partial | ✓ |
| Privacy | ✗ | ✗ | ✗ | ✓ |
| Free / No API key | ✗ | ✗ | ✗ | ✓ |
mcp-searxng is a standalone MCP server — a separate Node.js process that your AI assistant connects to for web search. It queries any SearXNG instance via its HTTP JSON API.
Not a SearXNG plugin: This project cannot be installed as a native SearXNG plugin. Point it at any existing SearXNG instance by setting
SEARXNG_URL.
AI Assistant (e.g. Claude)
│ MCP protocol
▼
mcp-searxng (this project — Node.js process)
│ HTTP JSON API (SEARXNG_URL)
▼
SearXNG instance
searxng_web_search
query (string): The search query. This string is passed to external search services.pageno (number, optional): Search page number, starts at 1 (default 1)time_range (string, optional): Filter results by time range - one of: "day", "week", "month", "year" (default: none)language (string, optional): Language code for results (e.g., "en", "fr", "de") or "all" (default: "all")safesearch (number, optional): Safe search filter level (0: None, 1: Moderate, 2: Strict) (default: instance setting)min_score (number, optional): Minimum relevance score from 0.0 to 1.0. Results below this score are filtered out.num_results (number, optional): Maximum number of results to return, from 1 to 20. SEARXNG_MAX_RESULTS applies as an operator ceiling.categories (string, optional): Comma-separated SearXNG categories (e.g. "news", "it,science"). When live /config is available, values are trimmed and normalized case-insensitively to the instance's canonical category names; unknown values are rejected with available categories listed. If /config is unavailable, values are forwarded as-is with a warning. Default: SearXNG instance default.engines (string, optional): Comma-separated SearXNG engine names (e.g. "google,bing,ddg", "semantic scholar"). When live /config is available, values are trimmed and normalized case-insensitively to canonical engine names, including engines disabled by default; unknown values are rejected with available engines listed. If /config is unavailable, values are forwarded as-is with a warning.response_format (string, optional): Response format, either "text" for formatted agent-readable output or "json" for raw SearXNG JSON with filtered/sliced results. (default: "text")searxng_search_suggestions
query (string): Partial or complete query to autocomplete.language (string, optional): Language code for suggestions (e.g., "en", "fr", "de") or "all" (default: "all")searxng_instance_info
includeEngines (boolean, optional): Include enabled engine names in the response. (default: false)includeDisabled (boolean, optional): Include disabled engine names when includeEngines is true. (default: false)category (string, optional): Filter categories and engines to a single category name.refresh (boolean, optional): Bypass the process cache and fetch fresh /config data. (default: false)web_url_read
url (string): The URL to fetch and processstartChar (number, optional): Starting character position for content extraction (default: 0)maxLength (number, optional): Maximum number of characters to returnsection (string, optional): Extract content under a specific heading (searches for heading text)paragraphRange (string, optional): Return specific paragraph ranges (e.g., '1-5', '3', '10-')readHeadings (boolean, optional): Return only a list of headings instead of full contentnpm install -g mcp-searxng
{
"mcpServers": {
"searxng": {
"command": "mcp-searxng",
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
Pre-built image:
docker pull isokoliuk/mcp-searxng:latest
Image signatures can be verified with Cosign — see SECURITY.md for instructions.
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "SEARXNG_URL",
"isokoliuk/mcp-searxng:latest"
],
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
}
}
}
}
To pass additional env vars, add -e VAR_NAME to args and the variable to env.
Build locally:
docker build -t mcp-searxng:latest -f Dockerfile .
Use the same config above, replacing isokoliuk/mcp-searxng:latest with mcp-searxng:latest.
docker-compose.yml:
services:
mcp-searxng:
image: isokoliuk/mcp-searxng:latest
stdin_open: true
environment:
- SEARXNG_URL=YOUR_SEARXNG_INSTANCE_URL
# Add optional variables as needed — see CONFIGURATION.md
MCP client config:
{
"mcpServers": {
"searxng": {
"command": "docker-compose",
"args": ["run", "--rm", "mcp-searxng"]
}
}
}
By default the server uses STDIO. Set MCP_HTTP_PORT to enable HTTP mode:
{
"mcpServers": {
"searxng-http": {
"command": "mcp-searxng",
"env": {
"SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
"MCP_HTTP_PORT": "3000"
}
}
}
}
Endpoints: POST/GET/DELETE /mcp (MCP protocol), GET /health (health check)
Test it:
MCP_HTTP_PORT=3000 SEARXNG_URL=http://localhost:8080 mcp-searxng
curl http://localhost:3000/health
Set SEARXNG_URL to your SearXNG instance URL. All other variables are optional.
Full environment variable reference: CONFIGURATION.md
Your SearXNG instance likely has JSON format disabled. Edit settings.yml (usually /etc/searxng/settings.yml):
search:
formats:
- html
- json
Restart SearXNG (docker restart searxng) then verify:
curl 'http://localhost:8080/search?q=test&format=json'
You should receive a JSON response. If not, confirm the file is correctly mounted and YAML indentation is valid.
See also: SearXNG settings docs · discussion
If you must use a public instance you don't control and it rejects format=json (the 403 above), set the opt-in flag instead of editing the server:
"SEARXNG_HTML_FALLBACK": "true"
A search that gets a 403/404 or a non-JSON response is then retried automatically without format=json and parsed from the regular HTML results page.
sourceFormat: "html" in JSON mode, and text mode adds the line "Note: Results parsed from SearXNG HTML fallback; metadata is limited." Relevance scores and engine names are not available from HTML.429), auth (401), or 5xx — the original error is surfaced unchanged. The fallback only triggers on 403/404/non-JSON, never on auth or network errors.Enabling JSON on an instance you control (above) remains the recommended setup — the fallback is a compatibility aid, not a replacement.
See CONTRIBUTING.md
MIT — see LICENSE for details.
SEARXNG_URL*URL of your SearXNG instance
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp