위키백과 API와 원활하게 연동되는 MCP 서버입니다. 이 도구를 사용하면 LLM을 사용하여 위키백과 콘텐츠를 검색하고 불러올 수 있습니다! 🤖!
https://github.com/user-attachments/assets/b5d9c5f3-a60e-48ea-8b4b-f1a7524d4fbb
🔍 사용자 정의 가능한 위키 사이트로 위키 페이지를 검색하세요. 예: wikipedia.org, fandom.com, wiki.gg 등!
📖 자세한 페이지 콘텐츠 검색
Related MCP server: mediawiki-mcp-server
장치에 uv가 설치되어 있는지 확인하세요.
클라이언트에서 구성:
서버는 기본적으로 https://en.wikipedia.org/를 사용합니다. 또한, 서버가 다른 위키 사이트를 검색하도록 설정할 수도 있습니다!
위키 사이트가 이 서버에서 작동하는지 확인하려면 MediaWiki 소프트웨어를 사용하는지 확인하세요(일반적으로 사이트 하단에 아이콘으로 표시됨).
더 자세히 확인하고 엔드포인트(일반적으로 https://mediawiki.org/ 와 같은 웹사이트 도메인)를 찾으려면 브라우저에서 base-url/rest.php/v1/page(예: https://noita.wiki.gg/rest.php/v1/page )로 이동하여 출력이 제대로 표시되는지 확인하세요. 출력이 제대로 표시되지 않으면 기본 URL에 '/w'를 추가하고 다시 시도해 보세요.
그런 다음 이 엔드포인트를 --base-url로 설정합니다.
지엑스피1
또는 소스에서 이 서버를 실행하려면 다음을 수행합니다.
{
"mcpServers": {
"mediawiki-mcp-server": {
"command": "uv",
"args": [
"run",
"--directory",
"mediawiki-mcp-server",
"path/to/project/src/mediawiki_mcp_server",
"--base-url", "https://example.com/"
],
"env": {
"HTTP_PROXY": "http://example.com:port"
}
}
}
}query : 검색어(가급적 짧고 집중적)
limit : 반환할 결과의 최대 개수(기본값: 5)
title : 검색할 위키피디아 페이지의 정확한 제목
npx @modelcontextprotocol/inspector uv run mediawiki-mcp-server도움이 될 만한 몇 가지 문서는 다음과 같습니다.
이 서버는 개발 중입니다. 기여를 환영합니다! 이슈를 제출하거나 풀 리퀘스트를 보내주세요.
Cherry Studio : 여러 LLM 제공업체를 지원하는 데스크톱 클라이언트입니다. MCP도 지원됩니다.
Get a page from mediawiki.org Args: title: The title of the page to get, which can be found in title field of the search results Returns: The page content
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does (retrieves page content) but lacks critical behavioral details such as authentication requirements, rate limits, error handling, or whether it's a read-only operation (though implied by 'Get'). This leaves significant gaps for an agent to understand operational constraints.
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 efficiently structured with a clear purpose statement followed by labeled sections for Args and Returns. Every sentence adds value without redundancy, making it easy to parse and understand quickly.
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?
For a simple read operation with one parameter and no output schema, the description covers the basics (purpose, parameter hint, return type). However, without annotations or output schema, it lacks details on response format (e.g., structured data vs. raw text), error cases, or prerequisites, leaving some contextual gaps for reliable agent use.
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 description adds meaningful context for the single parameter 'title' by explaining that it 'can be found in title field of the search results,' which clarifies its source and usage. Since schema description coverage is 0% and there's only one parameter, this compensates well, though it doesn't detail format constraints like case sensitivity or special characters.
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 action ('Get a page') and resource ('from mediawiki.org'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from the sibling 'search' tool, which appears to be a related but distinct operation for finding pages rather than retrieving specific content.
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 no guidance on when to use this tool versus alternatives like the 'search' sibling. It mentions that titles 'can be found in title field of the search results,' which hints at a workflow but doesn't explicitly state when to choose get_page over search or other potential tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for a wiki page. The shorter the request, the better, preferably containing only the main term to be searched. Args: query: The query to search for limit: The number of results to return Returns: A list of pages that match the query
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the search returns a list of pages, which is helpful. However, it doesn't address important behavioral aspects like pagination, sorting, relevance ranking, error conditions, or performance characteristics. For a search tool with zero annotation coverage, this leaves significant gaps in understanding how the tool 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 concise with three clear sections: purpose statement, usage advice, parameter documentation, and return value. Each sentence serves a distinct purpose. The structure with labeled 'Args:' and 'Returns:' sections is helpful, though the formatting could be cleaner.
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?
For a search tool with 2 parameters, no annotations, and no output schema, the description provides basic but incomplete coverage. It explains what the tool does and documents parameters, but lacks details about the search algorithm, result format beyond 'list of pages,' error handling, or performance considerations. The absence of output schema means the description should ideally explain the return structure more thoroughly.
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?
Schema description coverage is 0%, so the schema provides no parameter documentation. The description explicitly documents both parameters: 'query: The query to search for' and 'limit: The number of results to return.' This adds meaningful semantics beyond the bare schema. However, it doesn't provide format guidance for the query or explain the default limit value (5 from schema).
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 for a wiki page.' It specifies the resource (wiki page) and action (search). However, it doesn't explicitly differentiate from the sibling tool 'get_page' - we can infer search returns multiple results while get_page likely retrieves a specific page, but this distinction isn't stated.
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 some usage guidance: 'The shorter the request, the better, preferably containing only the main term to be searched.' This offers practical advice but doesn't explicitly state when to use this tool versus the 'get_page' sibling. There's implied context that this is for finding pages rather than retrieving specific ones, but no explicit alternative guidance.
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.
get_pagesearchScored across 2 tools
The two tools have clearly distinct purposes: get_page retrieves specific page content by title, while search finds pages matching a query. There is no overlap in functionality, making it easy for an agent to select the correct tool based on the task.
Both tools follow a consistent verb_noun pattern (get_page and search, where search implies 'search_pages'). The naming is simple, predictable, and uses snake_case uniformly, providing clear readability.
With only 2 tools, the server feels thin for a MediaWiki domain, lacking essential operations like creating, updating, or deleting pages. While get_page and search cover basic retrieval, the scope is incomplete, making it borderline too few for practical use.
The tool surface is severely incomplete for a MediaWiki server, missing core CRUD operations (e.g., create_page, update_page, delete_page) and other common actions like listing categories or handling user interactions. This will likely cause agent failures in broader workflows.
An MCP server that gives your AI access to the source code and docs of all public github repos
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
MCP server for AI dialogue using various LLM models via AceDataCloud
