A
licenseB
qualityC
maintenanceProvides web search capabilities using SearxNG, allowing AI assistants like Claude to search the web with a privacy-respecting metasearch engine.
1
11
MIT
Marginalia MCP Server
by bmorphism
边注 MCP 服务器
MCP（模型上下文协议）服务器提供对Marginalia Search 的访问，Marginalia Search 是一个专注于查找非商业内容和互联网隐藏瑰宝的搜索引擎。
特征
使用 Marginalia Search API 搜索网页
可配置的搜索参数包括索引和结果计数
带有有用错误消息的速率限制保护
使用 MCP SDK 构建，实现无缝集成
Related MCP server: web-search-mcp
安装
npm install
npm run build配置
可以使用环境变量来配置服务器：
MARGINALIA_API_KEY：您的 Marginalia Search API 密钥（可选，默认为公开访问）
要申请专用 API 密钥，请联系： kontakt@marginalia.nu
用法
服务器提供以下MCP工具：
搜索
使用 Marginalia Search 按照以下参数搜索网页：
query（必需）：搜索查询字符串index（可选）：搜索索引号（对应于主 GUI 中的下拉菜单）count（可选）：返回的结果数（1-100，默认值：10）
通过 MCP 使用的示例：
const result = await mcp.useTool("marginalia", "search", {
query: "interesting non-commercial websites",
count: 5
});响应格式
搜索结果以以下格式返回：
{
"query": "your search query",
"license": "license information",
"results": [
{
"url": "result url",
"title": "page title",
"description": "page description"
}
// ... more results
]
}错误处理
该服务器包括强大的错误处理功能：
速率限制（503 条回复）
无效请求
网络错误
API 特定错误
添加文本转语音支持
要使用 say MCP 服务器启用文本转语音功能，请添加以下配置：
对于 Cline（VSCode 扩展）
添加到~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json ：
{
"mcpServers": {
"say": {
"command": "node",
"args": ["/Users/barton/worlds/servers/src/say-mcp-server/build/index.js"]
}
}
}对于克劳德桌面
添加到~/Library/Application Support/Claude/claude_desktop_config.json ：
{
"mcpServers": {
"say": {
"command": "node",
"args": ["/Users/barton/worlds/servers/src/say-mcp-server/build/index.js"]
}
}
}Say MCP 服务器提供文本转语音功能，支持多种语音和语言。可用工具：
speak：使用指定的声音和速率大声朗读文本list_voices：列出所有可用的文本转语音声音
执照
MIT 许可证 - 详情请参阅许可证文件
Available Tools
1 toolsearch-marginaliaC
Search the web using Marginalia Search
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results to return | |
| index | No | Search index (corresponds to dropdown in main GUI) | |
| query | Yes | Search query |
TDQS
C2.9/5.0
Behavior2/5
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 'Search the web' but fails to describe key behaviors such as rate limits, authentication needs, result format, or error handling. This leaves significant gaps in understanding how the tool operates beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—a single sentence that directly states the tool's function without any fluff or redundancy. It is front-loaded and wastes no words, making it efficient for quick comprehension by an AI agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It covers the basic purpose but misses critical context like behavioral traits, result format, and error handling. For a search tool with three parameters and no structured output information, this minimal description leaves too many operational details unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, documenting all three parameters (query, count, index) clearly. The description adds no additional semantic context beyond what the schema provides, such as examples or usage tips. With high schema coverage, the baseline score of 3 is appropriate, as the description doesn't compensate but doesn't need to heavily.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
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 Marginalia Search.' It specifies the verb ('Search') and the resource ('the web'), and mentions the specific search engine ('Marginalia Search'). However, since there are no sibling tools, it cannot differentiate from alternatives, which prevents a perfect score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or contextual constraints. It simply states what the tool does without indicating scenarios where it might be preferred or avoided, leaving the agent with no usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
search-marginalia
TDQS
B3.1/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'search-marginalia' has a clear and distinct purpose of searching the web using Marginalia Search, leaving no room for confusion or misselection.
Naming Consistency5/5
Since there is only one tool, naming consistency is inherently perfect. The tool name 'search-marginalia' follows a clear verb_noun pattern, and with no other tools to compare, there are no deviations or inconsistencies in naming conventions.
Tool Count2/5
A single tool for a web search server is too few for the apparent scope, as it lacks basic functionality like filtering results, handling pagination, or accessing specific search features. This minimal toolset feels thin and limits the server's utility, making it borderline inadequate for typical search-related tasks.
Completeness2/5
The tool surface is severely incomplete for a web search domain. While 'search-marginalia' provides a core search function, there are significant gaps such as no ability to refine searches, view result details, or manage search history. This will likely cause agent failures when more complex search operations are needed.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Marginalia MCP — independent web search over a non-commercial, non-SEO index.
Search the agentic web. 4,100+ sites, 11 tools incl. check_url + verify_mcp for probe-before-use.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Search indexed websites, read raw page markdown, and score AI visibility for any site.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceProvides ad-filtered web search and full-page content reading, including multi-page and JavaScript-rendered pages, with source verification and configurable search providers.-
rabbytte-mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables assistants to search and ask questions against a human-curated search engine index, returning vetted sites with titles, URLs, descriptions, tags, and cited answers. Runs locally over stdio with no API key or signup required.53 npm1MIT- AlicenseNot gradedqualityBmaintenanceEnables independent web search over a non-commercial, non-SEO index that favors text-heavy, ad-light pages, useful for niche technical and historical topics.432 npmMIT