Perplexity MCP Server
Perplexity MCP 服务器
使用 Perplexity 的 API 提供网络搜索功能的 MCP 服务器。
先决条件
Node.js(v14 或更高版本)
Perplexity API 密钥(在https://www.perplexity.ai/settings/api获取)
克劳德桌面应用程序
Related MCP server: Perplexity Web Search MCP Server
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 Perplexity Server:
npx -y @smithery/cli install @jaacob/perplexity-mcp --client claude手动安装
克隆此存储库:
git clone https://github.com/jaacob/perplexity-mcp cd perplexity-mcp安装依赖项:
npm install构建服务器:
npm run build
配置
从https://www.perplexity.ai/settings/api获取您的 Perplexity API 密钥
将服务器添加到 Claude 的配置文件中,地址为
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"perplexity-server": {
"command": "node",
"args": [
"/absolute/path/to/perplexity-mcp/build/index.js"
],
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here",
"PERPLEXITY_MODEL": "sonar"
}
}
}
}将/absolute/path/to替换为您克隆存储库的实际路径。
可用型号
您可以通过设置PERPLEXITY_MODEL环境变量来指定要使用的模型。可用选项:
sonar-reasoning-pro- 推理能力最强的模型sonar-reasoning- 增强推理能力sonar-pro响应时间更快sonar默认模型(如果未指定模型则使用)
如需了解最新的模型定价和供货情况,请访问: https://docs.perplexity.ai/guides/pricing
用法
配置服务器并重启 Claude 后,你就可以简单地让 Claude 搜索信息了。例如:
“关于SpaceX有什么最新消息吗?”
“搜索芝加哥最好的餐厅”
“查找有关爵士乐历史的信息”
Claude 会自动使用 Perplexity 搜索工具来查找并返回相关信息。
如果出于某种原因它决定不这样做,您可以通过在提示前加上“搜索网络”来强制执行此问题。
发展
修改服务器:
编辑
src/index.ts使用
npm run build重建重新启动 Claude 以加载更改
执照
麻省理工学院
Available Tools
1 toolsearchC
Search the web using Perplexity AI
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The search query |
TDQS
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 specify rate limits, authentication requirements, result format, pagination, or any other behavioral characteristics. The description is minimal and lacks important operational context.
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 extremely concise - a single sentence that directly states the tool's function. There's zero waste or unnecessary verbiage. It's appropriately sized for a simple search tool and front-loaded with the essential information.
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 no annotations and no output schema, the description is insufficiently complete. It doesn't explain what kind of results to expect, whether there are limitations on query types, how results are formatted, or any other operational details. The description leaves too many questions unanswered for effective tool usage.
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 100% description coverage with the 'query' parameter clearly documented. The description doesn't add any additional parameter semantics beyond what's already in the schema. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no parameter information in the description.
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 ('Search the web') and specifies the resource/context ('using Perplexity AI'), making the purpose immediately understandable. It's not a tautology and provides specific information about what the tool does. However, since there are no sibling tools mentioned, it cannot demonstrate differentiation from alternatives.
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, prerequisites, or specific contexts where it's most appropriate. It simply states what the tool does without any usage context 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
v1.0.0- First observed
search
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools, making disambiguation perfect. The tool's purpose is clearly defined as web search using Perplexity AI, leaving no room for misselection.
A single tool named 'search' follows a consistent and straightforward verb-based naming pattern. There are no other tools to compare against, so no inconsistency can exist in the naming scheme.
One tool is too few for a server named 'Perplexity MCP Server', which implies broader capabilities beyond just search. A single tool feels thin and under-scoped for what might be expected from a Perplexity AI integration, such as additional operations like summarization or follow-up queries.
The tool surface is severely incomplete for a web search domain; it only offers a basic search function without any complementary tools for refining results, getting summaries, or handling related queries. This creates significant gaps that could lead to agent failures in complex tasks.
Maintenance
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, agentic search, news, page retrieval, sitemaps, and trending topics through Search1API.
Related MCP Servers
- AlicenseBqualityFmaintenanceA server facilitating web search functionality by utilizing Perplexity AI's API, designed to integrate with the Claude desktop client for enhanced search queries.1308MIT
- FlicenseNot gradedqualityDmaintenanceAllows Claude or other MCP-compatible AI assistants to search the web and get up-to-date information using the Perplexity API, with features for filtering results by time period.8-
- AlicenseNot gradedqualityDmaintenanceIntegrates the Sonar API to provide Claude with real-time web-wide research capabilities. Enables conversational web searches through Perplexity's AI-powered search engine for up-to-date information retrieval.1,406 npmMIT
- AlicenseNot gradedqualityDmaintenanceExposes Perplexity AI's search capabilities to Claude, enabling real-time web search and information retrieval within the assistant. The project is currently in active development with plans to support Perplexity Spaces and multi-source data synthesis.Apache 2.0