SearXNG HTTP MCP MCP Server
io.github.whw23/searxng-http-mcp
Self-contained SearXNG metasearch MCP server with 200+ engines, privacy-first, and zero-install Docker deployment.
What is the SearXNG HTTP MCP MCP server?
The SearXNG HTTP MCP server is a self-contained MCP wrapper around SearXNG, a free privacy-respecting metasearch engine aggregating results from 200+ search engines. It provides search, autocomplete, and engine discovery tools via HTTP, stdio, or uvx, with built-in authentication and a reverse-proxied Web UI.
SearXNG HTTP MCP gives Claude and other MCP clients access to privacy-first web search across 200+ engines organized into 30+ categories (general, news, images, videos, science, IT, etc.). Deploy once as a Docker container and connect any client; no external API keys required. Features multi-page fanout, autocomplete suggestions, engine metadata discovery, and optional API key authentication.
How to install SearXNG HTTP MCP
Copy-paste configuration for popular MCP clients.
API_KEYsecretAPI key for authentication. Leave empty for no auth.
Tools & capabilities
Tools this server exposes to the agent.
search— Search the web using SearXNG, aggregating results from 200+ search engines. Supports category filtering, engine selection, language specification, and multi-page fanout.autocomplete— Get autocomplete suggestions for search queries to discover relevant search terms.engine_discovery— Query available search engines grouped by category to explore SearXNG's engine coverage.
Use cases
- Search the web across 200+ engines with privacy, filtering by category (news, science, images, etc.) or specific engines
- Discover relevant search terms via autocomplete suggestions while composing queries
- Explore which search engines are available in specific categories before running targeted searches
- Conduct multi-page web research by fanning out searches across multiple result pages in a single call
- Build privacy-respecting AI agents that need web access without relying on commercial search APIs
SearXNG HTTP MCP MCP server FAQ
It's a self-contained MCP server that wraps SearXNG, a free metasearch engine. It aggregates results from 200+ search engines (Google, Bing, DuckDuckGo, Brave, etc.) and exposes search, autocomplete, and engine discovery tools to Claude and other MCP clients.
Yes. SearXNG HTTP MCP is free and open-source. It requires no external API keys or paid subscriptions. You deploy it yourself via Docker or uvx.
Add it as an MCP server in your client config. For HTTP mode, run `docker run -d -p YOUR_PORT:8888 ghcr.io/whw23/searxng-http-mcp:latest` and point your client to `http://YOUR_HOST:YOUR_PORT/mcp/`. For stdio mode, use `docker run --rm -i ghcr.io/whw23/searxng-http-mcp:latest --stdio`.
No, authentication is optional. Set the `API_KEY` environment variable to enable `x-api-key` header or HTTP Basic Auth. Without it, all requests are open.
It's self-contained (SearXNG built into the Docker image), supports HTTP + stdio + uvx transport, includes authentication, exposes all SearXNG capabilities (30+ categories, autocomplete, engine metadata), and reverse-proxies the SearXNG Web UI on the same port.
Yes. In uvx mode, set `SEARXNG_URL=http://YOUR_SEARXNG_HOST:PORT` to point to an existing SearXNG instance. In Docker mode, the server runs SearXNG internally.
README (reference)
Source of truth, from the repository.
<a href="https://glama.ai/mcp/servers/whw23/searxng_http_mcp"><img width="380" height="200" src="https://glama.ai/mcp/servers/whw23/searxng_http_mcp/badge" alt="searxng-http-mcp MCP server"></a>
<p> <a href="README.zh-CN.md">中文</a> · <a href="#-quick-start">Quick Start</a> · <a href="#-features">Features</a> · <a href="#-architecture">Architecture</a> · <a href="#-comparison-with-alternatives">Comparison</a> · <a href="#-usage">Usage</a> · <a href="#-mcp-tools-reference">MCP Tools</a> · <a href="#-client-configuration">Client Config</a> · <a href="#-ai-coding-agent-plugin">Plugin</a> · <a href="#-contributing">Contributing</a> </p> </div>A self-contained MCP server that wraps SearXNG — a free, privacy-respecting metasearch engine that aggregates results from 200+ search engines.
🚀 Quick Start
Server mode — deploy once, connect from any client:
docker run -d --name searxng-mcp --restart unless-stopped \
-p YOUR_PORT:8888 --memory=512m --cpus=1 \
ghcr.io/whw23/searxng-http-mcp:latest
Then connect your client to http://YOUR_HOST:YOUR_PORT/mcp/. To enable API key auth, see Authentication.
Local mode — no server needed, run directly in your client:
docker run --rm -i --memory=512m --cpus=1 ghcr.io/whw23/searxng-http-mcp:latest --stdio
Add this as a stdio MCP server in your client — see Client Configuration for details.
uvx mode — if you already have SearXNG running (install guide):
uvx searxng-http-mcp
Set SEARXNG_URL to point to your SearXNG instance (default: http://127.0.0.1:8080).
✨ Features
Search
- 🔍 200+ search engines — Google, Bing, DuckDuckGo, Brave, and more via SearXNG
- 📂 30+ categories — news, images, videos, science, IT, and more
- 📄 Multi-page fanout — up to 5 pages per call
- 💡 Autocomplete suggestions — discover relevant search terms
- 🗂 Engine discovery — query available engines grouped by category
- 🎯 Token-efficient — results trimmed to essentials
Infrastructure
- 📦 Self-contained — SearXNG built into Docker image
- 🔄 Triple transport — HTTP server, Docker stdio, and uvx standalone
- 🔐 Authentication —
x-api-key+ HTTP Basic Auth - 🌐 Reverse proxy — SearXNG Web UI on the same port
- ⚡ Dynamic tool descriptions — live category lists injected at startup
- 📐 Rich JSON Schema — enum constraints, range limits, and descriptions on every parameter
🏛 Architecture
graph LR
Client(["client:YOUR_PORT"]) --> Expose(":8888")
subgraph Container["🐳 Docker Container"]
direction LR
Expose --> Auth{Auth}
Auth -->|/mcp| MCP[FastMCP Server]
Auth -->|/*| Proxy[Reverse Proxy]
MCP --> SearXNG[SearXNG :8080]
Proxy --> SearXNG
end
style Expose fill:none,stroke:#2496ed,stroke-dasharray:5 5,color:#2496ed
style Client fill:#4a90d9,color:#fff,stroke:#3a7bc8
style Container fill:#f0f4f8,stroke:#2496ed,stroke-width:2px,color:#2496ed
style Auth fill:#f5a623,color:#fff,stroke:#d4900e
style MCP fill:#50c878,color:#fff,stroke:#3da85e
style Proxy fill:#9b59b6,color:#fff,stroke:#8344a5
style SearXNG fill:#e74c3c,color:#fff,stroke:#c0392b
📊 Comparison with Alternatives
<details> <summary>Why these five?</summary>There are 20+ SearXNG MCP servers and many more general-purpose search MCPs. Most SearXNG wrappers only expose a basic search tool, leaving SearXNG's categories, autocomplete, and engine metadata unused. We picked five alternatives that each represent a distinct category:
- 88plug/searxng-mcp — richest tool surface among SearXNG MCPs (7 tools: rendered fetch, research mode, parallel queries)
- ihor/mcp-searxng — most GitHub stars among SearXNG MCPs
- open-webSearch — top free multi-engine alternative outside the SearXNG ecosystem (Bing, Baidu, DuckDuckGo, Brave, etc.)
- exa-mcp-server — most popular commercial search API MCP
- Perplexity MCP — commercial AI-powered search, highest star count in the search MCP space
MCP is designed for composition — clients connect multiple specialized servers, each doing one thing well. Some alternatives bundle URL fetching, rendered page extraction, multi-query fan-out, or research modes into the search server. We keep the tool surface to three (search, autocomplete, engine discovery) by design:
- URL fetching is a separate concern. MCP clients already ship dedicated tools (WebFetch, Playwright MCP, Jina Reader). Bundling fetch into a search server mixes responsibilities and duplicates the client ecosystem.
- Multi-query parallel search is client-side orchestration. LLM clients can fire multiple
searchcalls in parallel — asearch_manytool only adds token overhead for tool selection with no real benefit. - Research / synthesis belongs in the LLM layer. The model is the best synthesizer. Pushing multi-step research logic into the MCP server couples application concerns to infrastructure.
Instead we invest in what the alternatives above lack: complete SearXNG API coverage (categories, autocomplete, engine metadata — capabilities most wrappers leave on the table), self-contained deployment, authentication, Web UI reverse proxy, and AI coding agent plugin integration (Claude Code / Copilot CLI / Codex CLI).
</details>📖 Usage
🌐 HTTP Mode (default)
# Without authentication
docker run -d --name searxng-mcp --restart unless-stopped \
-p YOUR_PORT:8888 --memory=512m --cpus=1 \
ghcr.io/whw23/searxng-http-mcp:latest
# With authentication
docker run -d --name searxng-mcp --restart unless-stopped \
-p YOUR_PORT:8888 --memory=512m --cpus=1 \
-e API_KEY=your-secret-key \
ghcr.io/whw23/searxng-http-mcp:latest
📡 stdio Mode
docker run --rm -i --memory=512m --cpus=1 \
ghcr.io/whw23/searxng-http-mcp:latest --stdio
No ports exposed. Communication via stdin/stdout. SearXNG runs internally for the MCP tools.
🐍 uvx Mode
# Connect to a local SearXNG instance (default: http://127.0.0.1:8080)
uvx searxng-http-mcp
# Connect to a remote SearXNG instance
SEARXNG_URL=http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT uvx searxng-http-mcp
Requires Python 3.14+ and an existing SearXNG instance. No Docker needed.
⚙️ Environment Variables
<table> <thead> <tr><th>Variable</th><th>Default</th><th>Description</th></tr> </thead> <tbody> <tr><td><code>API_KEY</code></td><td><em>(empty, no auth)</em></td><td>API key for authentication</td></tr> <tr><td><code>SEARXNG_URL</code></td><td><code>http://127.0.0.1:8080</code></td><td>SearXNG instance URL (for uvx/standalone mode)</td></tr> </tbody> </table>🔐 Authentication
When API_KEY is set, all requests require one of:
x-api-keyheader — for MCP clients:x-api-key: your-key- HTTP Basic Auth — for browsers
[!TIP] Browser Login: When accessing the Web UI with
<img src="assets/browser_login.svg" alt="Browser Login Dialog" width="420">API_KEYenabled, the browser will show a login dialog. Leave the username empty and enter your API key as the password.
When API_KEY is not set, all requests are open.
🔧 MCP Tools Reference
<details> <summary>🔍 <code>search</code> — Search the web using SearXNG</summary> <br>Aggregates results from 200+ search engines with privacy.
<table> <thead> <tr><th>Parameter</th><th>Type</th><th>Required</th><th>Default</th><th>Description</th></tr> </thead> <tbody> <tr><td><code>query</code></td><td>string</td><td>yes</td><td>—</td><td>The search query to use</td></tr> <tr><td><code>categories</code></td><td>string</td><td>no</td><td>""</td><td>Comma-separated category names (e.g., <code>general,news,science</code>)</td></tr> <tr><td><code>engines</code></td><td>string</td><td>no</td><td>""</td><td>Comma-separated engine names (e.g., <code>google,arxiv,wikipedia</code>)</td></tr> <tr><td><code>language</code></td><td>string</td><td>no</td><td>""</td><td>Search language code (e.g., <code>en</code>, <code>zh</code>, <code>ja</code>)</td></tr> <tr><td><code>time_range</code></td><td>enum</td><td>no</td><td>null</td><td><code>day</code>, <code>week</code>, <code>month</code>, <code>year</code></td></tr> <tr><td><code>safesearch</code></td><td>enum</td><td>no</td><td>0</td><td><code>0</code>=off, <code>1</code>=moderate, <code>2</code>=strict</td></tr> <tr><td><code>pageno</code></td><td>int ≥1</td><td>no</td><td>1</td><td>Starting page number</td></tr> <tr><td><code>pages</code></td><td>int 1–5</td><td>no</td><td>1</td><td>Number of pages to fetch in parallel</td></tr> <tr><td><code>max_results</code></td><td>int 1–100</td><td>no</td><td>10</td><td>Maximum number of results to return</td></tr> <tr><td><code>format</code></td><td>enum</td><td>no</td><td>compact</td><td><code>compact</code> (title/url/content) or <code>full</code> (+ engines/score/category/date)</td></tr> </tbody> </table>Returns: results, answers, suggestions, corrections, infoboxes.
</details> <details> <summary>💡 <code>autocomplete</code> — Get search query suggestions</summary> <br> <table> <thead> <tr><th>Parameter</th><th>Type</th><th>Required</th><th>Description</th></tr> </thead> <tbody> <tr><td><code>query</code></td><td>string</td><td>yes</td><td>Partial query string to get suggestions for</td></tr> </tbody> </table> </details> <details> <summary>🗂 <code>engine_info</code> — Discover available engines and categories</summary> <br>No parameters. Returns the list of enabled engines grouped by category.
Returns:
{
"categories": ["general", "images", "videos", "news", ...],
"engines": ["google", "bing", "duckduckgo", ...],
"category_engines": {
"general": ["google", "bing", "duckduckgo", "brave", ...],
"science": ["arxiv", "google scholar", "pubmed", ...],
...
}
}
Use this to discover what engines are available before calling search with specific engines or categories filters.
🔌 Client Configuration
The following is a baseline server-mode (remote HTTP) example using the standard mcpServers JSON structure. Many clients accept this structure, but field names and required type values differ — see the NOTE below and adjust for your client:
{
"mcpServers": {
"searxng": {
"type": "http",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
<details> <summary><img src="assets/icons/claude.svg" height="16" alt="Claude"> <b>Claude Desktop</b></summary>[!NOTE] Field-name differences: ZCode uses
mcp.servers; Kilo Code uses a top-levelmcpkey with"type": "remote"; Windsurf usesserverUrlinstead ofurl; VS Code Copilot uses a top-levelserverskey; OpenCode nests undermcpwith"type": "remote"; Codex and Hermes usemcp_servers(TOML/YAML). For Claude Code,"type": "http"is required — without it the entry is read as a stdio server and skipped. For Cline, set"type": "streamableHttp"on remote HTTP servers.
Server mode — edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"searxng": {
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
Server mode (CLI):
claude mcp add --transport http searxng http://YOUR_HOST:YOUR_PORT/mcp/ \
--header "x-api-key: your-secret-key"
Server mode (JSON) — the same mcpServers structure works in a team-shared project .mcp.json or a user-wide global ~/.claude.json:
{
"mcpServers": {
"searxng": {
"type": "http",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
claude mcp add --transport stdio searxng -- docker run --rm -i --memory=512m --cpus=1 ghcr.io/whw23/searxng-http-mcp:latest --stdio
uvx mode:
claude mcp add --transport stdio searxng -- uvx searxng-http-mcp
Server mode — add to ~/.codex/config.toml:
[mcp_servers.searxng]
url = "http://YOUR_HOST:YOUR_PORT/mcp/"
http_headers = { "x-api-key" = "your-secret-key" }
Local mode:
[mcp_servers.searxng]
command = "docker"
args = ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
uvx mode:
[mcp_servers.searxng]
command = "uvx"
args = ["searxng-http-mcp"]
Server mode — edit .cursor/mcp.json:
{
"mcpServers": {
"searxng": {
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
Server mode — add to .vscode/mcp.json:
{
"servers": {
"searxng": {
"type": "http",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"servers": {
"searxng": {
"type": "stdio",
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"servers": {
"searxng": {
"type": "stdio",
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
Server mode — add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"searxng": {
"serverUrl": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
Configure via Cline's MCP settings panel in VS Code (Cline > MCP Servers > Add).
Server mode:
{
"mcpServers": {
"searxng": {
"type": "streamableHttp",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
Server mode — edit opencode.json:
{
"mcp": {
"searxng": {
"type": "remote",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcp": {
"searxng": {
"type": "local",
"command": ["docker", "run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcp": {
"searxng": {
"type": "local",
"command": ["uvx", "searxng-http-mcp"]
}
}
}
Server mode — edit ~/.hermes/config.yaml:
mcp_servers:
searxng:
url: "http://YOUR_HOST:YOUR_PORT/mcp/"
headers:
x-api-key: "your-secret-key"
Local mode:
mcp_servers:
searxng:
command: "docker"
args: ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
uvx mode:
mcp_servers:
searxng:
command: "uvx"
args: ["searxng-http-mcp"]
Server mode — edit ~/.zcode/cli/config.json (user-wide) or .zcode/config.json (project):
{
"mcp": {
"servers": {
"searxng": {
"type": "http",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
}
Local mode:
{
"mcp": {
"servers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
}
uvx mode:
{
"mcp": {
"servers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
}
ZCode also accepts the standard mcpServers structure (e.g. in .agents/mcp.json). Alternatively, add servers via Settings → MCP Servers → New MCP Server.
Server mode — edit ~/.config/kilo/kilo.jsonc (global) or .kilo/kilo.jsonc (project):
{
"mcp": {
"searxng": {
"type": "remote",
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
},
"enabled": true
}
}
}
Local mode:
{
"mcp": {
"searxng": {
"type": "local",
"command": ["docker", "run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"],
"enabled": true
}
}
}
uvx mode:
{
"mcp": {
"searxng": {
"type": "local",
"command": ["uvx", "searxng-http-mcp"],
"environment": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" },
"enabled": true
}
}
}
Install the MCP adapter once, then add a standard mcpServers block — e.g. in ~/.pi/agent/mcp.json (all projects) or .pi/mcp.json (project):
pi install npm:pi-mcp-adapter
Restart Pi after installing.
Server mode:
{
"mcpServers": {
"searxng": {
"url": "http://YOUR_HOST:YOUR_PORT/mcp/",
"headers": {
"x-api-key": "your-secret-key"
}
}
}
}
Local mode:
{
"mcpServers": {
"searxng": {
"command": "docker",
"args": ["run", "--rm", "-i", "--memory=512m", "--cpus=1", "ghcr.io/whw23/searxng-http-mcp:latest", "--stdio"]
}
}
}
uvx mode:
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": ["searxng-http-mcp"],
"env": { "SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT" }
}
}
}
🧩 AI Coding Agent Plugin
Compatible with Claude Code, GitHub Copilot CLI, and OpenAI Codex CLI. Add the marketplace, then install the plugin that fits your setup:
/plugin marketplace add whw23/searxng_http_mcp
All plugins include:
- 🔍
/web-search-via-searxngskill — search the web with category selection guide and usage rules - 🤖
web-searcheragent — research subagent with:- 🌐 Multi-language parallel search — auto-detects query language, searches in multiple languages for broader coverage
- 🛡 Source credibility tiers — Tier 1/2/3 classification with AI poisoning defense
- ✅ Cross-validation — key facts require 2+ independent sources
- 🔍 WebFetch deep reading — reads full pages from credible sources, not just snippets
- 🔄 Multi-round iterative search — up to 3 rounds with automatic deepening on gaps
- ⏱ Timeliness evaluation — flags outdated content, states source date ranges
- 📝 Footnote-style references — structured output with inline source citations
/plugin install searxng-http-mcp-standalone@searxng-http-mcp
Runs via uvx. Requires Python 3.14+ and an existing SearXNG instance. Set SEARXNG_URL in ~/.claude/settings.json:
{
"env": {
"SEARXNG_URL": "http://YOUR_SEARXNG_HOST:YOUR_SEARXNG_PORT"
}
}
/plugin install searxng-http-mcp@searxng-http-mcp
Runs SearXNG in a local Docker container via stdio. Requires Docker installed.
</details> <details> <summary>🌐 <b>Remote mode</b> — connect to a deployed server via HTTP</summary> <br>/plugin install searxng-http-mcp-remote@searxng-http-mcp
Connects to a deployed SearXNG MCP server. Requires env vars SEARXNG_MCP_URL and SEARXNG_API_KEY.
Add to ~/.claude/settings.json under the env field:
{
"env": {
"SEARXNG_MCP_URL": "http://YOUR_HOST:YOUR_PORT/mcp/",
"SEARXNG_API_KEY": "your-api-key"
}
}
Then restart Claude Code.
</details>🛠 SearXNG Configuration
<details> <summary>🖥 <b>Via Web UI</b></summary> <br>Access the SearXNG Web UI at http://YOUR_HOST:YOUR_PORT/ to configure search engines, languages, and other settings. Changes persist during the container's lifetime.
Mount the SearXNG config directory for persistent configuration:
docker run -d --name searxng-mcp --restart unless-stopped \
-p YOUR_PORT:8888 --memory=512m --cpus=1 \
-v /path/to/searxng-config:/etc/searxng \
ghcr.io/whw23/searxng-http-mcp:latest
SearXNG generates settings.yml on first startup. The container automatically enables JSON format output required by MCP tools.
🏗 Build from Source
git clone https://github.com/whw23/searxng_http_mcp.git
cd searxng_http_mcp
docker build -t searxng-http-mcp:local .
docker run -d --name searxng-mcp --restart unless-stopped \
-p YOUR_PORT:8888 --memory=512m --cpus=1 \
searxng-http-mcp:local
🤝 Contributing
See CONTRIBUTING.md for the full workflow, CI requirements, and development setup.
- 🍴 Fork the repository and enable GitHub Actions in your fork
- 🌿 Create a feature branch from
dev - ✍️ Make your changes
- ✅ Run tests:
pytest tests/ -v— CI must pass in your fork before opening a PR - 📬 Submit a PR to
dev
Development happens on the dev branch. Merges to main trigger image builds.
📄 License
MIT — MCP server code.
SearXNG itself is licensed under AGPL-3.0-or-later.
Related MCP servers
Ariadne
Deterministic local cross-service API-chain discovery for AI coding agents.
Toss Invest
Access Toss Securities market, account, and opt-in trading APIs through MCP.
Wick
Browser-grade web access for AI agents. Fetches any webpage, returns clean markdown.
Evidence-backed capital-change intelligence and sourced financial data for AI agents
View repository →
CNN Fear & Greed Index
CNN's Fear & Greed index for the US stock market: score, rating, indicators and daily history.
Read-only, self-hosted MCP access to IMAP email with local indexing and AI-powered search.