searXNGを介してエージェント システムを検索システムに接続するための MCP サーバー。
SearXNGでウェブを検索する
Related MCP server: SearXNG MCP Server
search(query: str) -> f"Searching for {query} using searXNG"クライアントのJSONを次のように設定します
{
"mcpServers": {
"searxng": {
"command": "uvx",
"args": [
"mcp-searxng"
]
}
}
}claude デスクトップにサーバーを追加します (エントリポイントは main.py です)
リポジトリをクローンし、このJSONをclaudeデスクトップに追加します
このサーバーはuvx mcp-searxngで実行することも、リポジトリのローカルコピーを使用することもできます。
{
"mcpServers": {
"searxng": {
"command": "uv",
"args": [
"--project",
"/absoloute/path/to/MCP-searxng/",
"run",
"/absoloute/path/to/MCP-searxng/mcp-searxng/main.py"
]
}
}
}環境に合わせてパスを変更する必要があります
環境変数SEARXNG_URL searxng サーバーの URL に設定します (デフォルトはhttp://localhost:8080 )
MCPクライアントを実行すると、searxngでWebを検索できるようになります。
注: claude デスクトップを使用している場合は、サーバーを再度実行する前に、必ずプロセスを終了してください (タスク マネージャーまたは同等のもの)。
search the web using searXNG. This will aggregate the results from google, bing, brave, duckduckgo and many others. Use this to find information on the web. Even if you do not have access to the internet, you can still use this tool to search the web.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions aggregation from multiple engines and offline capability, which adds some context, but fails to disclose critical traits like rate limits, authentication needs, result format, or pagination behavior. For a web search tool with zero annotation coverage, this leaves significant gaps in understanding how it behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with three sentences that are front-loaded: the first states the core purpose, the second explains aggregation, and the third adds usage context. Each sentence earns its place without redundancy, though minor trimming could improve flow.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (web search with aggregation), no annotations, no output schema, and low schema coverage, the description is partially complete. It covers the purpose and some usage context but misses behavioral details and output expectations. This is adequate as a minimum viable description but has clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter with 0% description coverage, so the description must compensate. It implies the 'query' parameter is for web searches but doesn't add specific meaning beyond that (e.g., syntax examples or constraints). Since schema coverage is low, the description provides minimal value, meeting the baseline for adequate but incomplete parameter information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'search the web using searXNG' with the specific verb 'search' and resource 'the web'. It explains that it aggregates results from multiple search engines (Google, Bing, etc.), which distinguishes it from a basic search tool. However, since there are no sibling tools mentioned, the differentiation aspect is not applicable, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear usage context: 'Use this to find information on the web' and notes it works even without internet access, which is helpful guidance. However, it lacks explicit when-not-to-use scenarios or alternatives, as there are no sibling tools to compare against, so it doesn't reach the highest score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0searchScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear, distinct purpose of web searching.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns or conventions.
One tool is too few for a web search server, as it lacks operations like filtering results, managing search history, or configuring engines. This minimal scope limits functionality and feels incomplete for the domain.
The tool surface is severely incomplete for web searching, offering only a basic search function. Missing are essential features like result pagination, advanced query options, or engine selection, which are typical in search APIs.
Free web search for AI agents. No API key required. Hosted MCP in active development.
MCP server for Google search results via SERP API
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
