A
licenseB
qualityF
maintenanceA server facilitating web search functionality by utilizing Perplexity AI's API, designed to integrate with the Claude desktop client for enhanced search queries.
1
307
MIT
Perplexity MCP Server
Perplexity MCP 서버
이는 Perplexity AI를 사용하여 웹을 검색할 수 있는 간단한 MCP 서버입니다.
설치
필수 조건
Node.js 18+ ( nodejs.org 에서 다운로드)
Git ( git-scm.com 에서 다운로드)
Perplexity AI API 키
Windows용 단계
저장소를 복제합니다.
지엑스피1
종속성 설치:
npm install환경 파일을 생성합니다.
루트 디렉토리에
.env라는 이름의 새 파일을 만듭니다.Perplexity AI API 키 GXP3를 추가하세요.
Related MCP server: Tavily MCP Server
Windows에서의 사용법
개발 모드
npm run dev생산 모드
프로젝트를 빌드하세요:
npm run build서버를 시작합니다:
npm startWindows 배치 파일 사용(권장)
Windows에서 환경 변수 문제를 방지하려면 포함된 배치 파일을 사용하세요.
먼저 프로젝트를 빌드하세요.
npm run build배치 파일을 실행합니다.
.\run-perplexity-server.bat또는 Windows 탐색기에서 run-perplexity-server.bat 파일을 두 번 클릭합니다.
자세한 지침은 Windows 설치 가이드를 참조하세요.
Windows 문제 해결
일반적인 문제
권한 오류
관리자 권한으로 명령 프롬프트 또는 PowerShell 실행
프로젝트 디렉토리의 파일 권한을 확인하세요
환경 변수
.env파일이 루트 디렉토리에 있는지 확인하세요..env파일에서=기호 주위에 공백이 없어야 합니다.환경 변수를 변경한 후 터미널을 다시 시작하세요.
제공된 배치 파일을 사용하여 환경 변수 문제를 방지하세요.
Node.js 문제
Node.js 설치 확인:
node --versionnpm이 설치되어 있는지 확인하세요:
npm --version
오류 메시지
Error: ENOENT: no such file or directory .가 표시되면 다음을 확인하세요.
모든 경로는 올바른 Windows 스타일 구분 기호를 사용합니다.
당신은 올바른 디렉토리에 있습니다
필요한 파일이 존재합니다
프로젝트 구조
perplexity-mcp-server/
├── src/
│ └── index.ts # Main server implementation
├── dist/ # Compiled output
├── .env # Environment variables
├── package.json # Project configuration
├── run-perplexity-server.bat # Windows batch file
└── tsconfig.json # TypeScript configurationAPI 사용
서버는 웹 검색을 위한 단일 도구인 perplexity_search 제공합니다.
{
"name": "perplexity_search",
"arguments": {
"query": "your search query here"
}
}특허
MIT
Available Tools
1 toolperplexity_searchC
Search the web using Perplexity AI
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query |
TDQS
C2.9/5.0
Behavior2/5
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. While 'Search the web' implies a read-only operation, it doesn't address critical aspects like rate limits, authentication requirements, response format, or whether it's a real-time search versus cached results. The description is too minimal for a tool that interacts with external services.
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 with zero wasted words. It's front-loaded with the core functionality and uses straightforward language. For a simple search tool, this level of brevity is appropriate.
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 that there are no annotations and no output schema, the description is insufficiently complete. It doesn't explain what kind of results to expect, whether there are usage limitations, or how the search differs from standard web searches. For a tool that presumably returns search results, more context about the output would be helpful.
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, with the single parameter 'query' clearly documented in the schema. The description doesn't add any additional semantic context about the parameter beyond what's already in the schema, so it meets the baseline score of 3.
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 action ('Search the web') and the resource/mechanism ('using Perplexity AI'), providing a specific verb+resource combination. However, with no sibling tools mentioned, there's no opportunity to distinguish from alternatives, so it cannot achieve 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 other search methods or alternatives. It simply states what the tool does without any context about appropriate use cases, prerequisites, or limitations.
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
- First observed
perplexity_search
TDQS
B3.2/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose, making it impossible for an agent to misselect between multiple options.
Naming Consistency5/5
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns. The name 'perplexity_search' follows a clear verb_noun format, but consistency cannot be assessed across a set of one.
Tool Count2/5
A single tool is generally too few for most server purposes, as it limits functionality and flexibility. For a web search server, this minimal scope might suffice for basic queries, but it feels thin and lacks auxiliary operations like filtering or advanced search options.
Completeness3/5
The server's purpose appears to be web search, and the single tool covers the core action of searching. However, there are notable gaps, such as no tools for refining searches, handling different search types (e.g., news, images), or managing search history, which could lead to agent workarounds or limitations.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Real-time web search, reasoning, and research through Perplexity's API
Enable AI assistants to perform web searches using Perplexity's Sonar Pro.
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Related MCP Servers
Tavily MCP Serverofficial
AlicenseAqualityDmaintenanceThis server enables AI systems to integrate with Tavily's search and data extraction tools, providing real-time web information access and domain-specific searches.426,297 npm2,415MIT- FlicenseBqualityNot gradedmaintenanceA server that allows AI assistants to perform web searches using Perplexity's sonar-deep-research model with citation support.111-
- AlicenseNot gradedqualityDmaintenanceA Type 3 DAuth MCP server for Perplexity AI API that provides web search, chat, embeddings, and content moderation using Perplexity's search-focused AI models.MIT