Skip to main content
Glama
enesjakozh
laodev1

Perplexity MCP Server

by laodev1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Perplexity MCP 服务器

概述

Perplexity MCP 服务器是 Anthropic 模型上下文协议 (MCP) 的 Node.js 实现，使 Claude 能够与 Perplexity 的语言模型进行交互。该服务器在 Claude 和 Perplexity AI 的功能之间搭建了安全的桥梁，允许通过使用工具增强 AI 交互。

Related MCP server: Perplexity MCP Server

可用工具

该服务器目前实现了两个主要工具：

1. perplexity_chat

先进的聊天完成工具，支持完整的消息历史记录。

{
  "name": "perplexity_chat",
  "description": "Generate a chat completion using Perplexity AI",
  "parameters": {
    "model": "string (optional) - One of: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online",
    "messages": "array of {role, content} objects - The conversation history",
    "temperature": "number (optional) - Sampling temperature between 0-2"
  }
}

2. perplexity_ask

简化的单一查询界面，用于快速提问。

{
  "name": "perplexity_ask",
  "description": "Send a simple query to Perplexity AI",
  "parameters": {
    "query": "string - The question or prompt to send",
    "model": "string (optional) - One of: llama-3.1-sonar-small-128k-online, llama-3.1-sonar-large-128k-online, llama-3.1-sonar-huge-128k-online"
  }
}

安装

  1. 克隆存储库：

    git clone https://github.com/yourusername/perplexity-mcp-server.git
cd perplexity-mcp-server

  2. 安装依赖项：

    npm install

  3. 创建.env文件：

    PERPLEXITY_API_KEY=your-api-key-here

  4. 构建项目：

    npm run build

Claude桌面配置

要将此服务器添加到 Claude Desktop，请更新您的claude_desktop_config.json ：

{
  "mcpServers": {
    //more servers...
    "perplexity": {
      "command": "node",
      "args": ["path\\to\\perplexity-mcp-server\\dist\\index.js"],
      "env": {
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY"
      }
    }
    //more servers...
  }
}

配置文件通常位于：

  • Windows： %APPDATA%/Claude/config/claude_desktop_config.json

  • macOS： ~/Library/Application Support/Claude/config/claude_desktop_config.json

  • Linux： ~/.config/Claude/config/claude_desktop_config.json

发展

启动开发服务器并自动重新编译：

npm run dev

服务器使用 TypeScript 并使用@modelcontextprotocol/sdk包实现 MCP 协议。

建筑学

核心组件

  1. PerplexityServer 类

    • 实现 MCP 服务器协议

    • 处理工具注册和执行

    • 管理错误处理和服务器生命周期

  2. 工具系统

    • 模块化工具定义

    • 类型安全的工具处理程序

    • 结构化输入验证

技术细节

  • 使用 TypeScript 构建以确保类型安全

  • 使用@modelcontextprotocol/sdk实现 MCP

  • 通过 stdio 传输进行通信

  • 基于环境的配置

错误处理

服务器实现了全面的错误处理：

  • API错误报告

  • 无效工具请求处理

  • 连接错误管理

  • 过程信号处理

依赖项

  • @modelcontextprotocol/sdk : ^1.0.3

  • dotenv ：^16.4.7

  • isomorphic-fetch ：^3.0.0

贡献

  1. 分叉存储库

  2. 创建你的功能分支（ git checkout -b feature/amazing-feature ）

  3. 提交您的更改（ git commit -m 'Add some amazing feature' ）

  4. 推送到分支（ git push origin feature/amazing-feature ）

  5. 打开拉取请求

安全

  • API 密钥通过环境变量进行管理

  • 所有工具参数的输入验证

  • 错误消息在输出前被清理

  • 通过 MCP 协议进行进程隔离

执照

该项目已获得 ISC 许可。

故障排除

常见问题及解决方案：

  1. 未找到服务器

    • 验证claude_desktop_config.json中的路径是否正确

    • 确保服务器已构建（ npm run build ）

    • 检查 Node.js 是否在你的 PATH 中

  2. 身份验证错误

    • 在 .env 中验证您的 Perplexity API 密钥

    • 检查 API 密钥是否具有所需的权限

  3. 工具执行错误

    • 验证工具参数与方案匹配

    • 检查网络连接

    • 查看服务器日志以获取详细的错误消息

Available Tools

2 tools
perplexity_askB

Send a simple query to Perplexity AI

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoThe model to use for completion
queryYesThe question or prompt to send

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations and a minimal description, the tool's behavior is opaque. It does not disclose whether the query is synchronous, what response format to expect, or any safety/reliability traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence that immediately conveys the tool's purpose. It is appropriately front-loaded and concise, though it could incorporate more detail without becoming wordy.

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?

For a simple query tool with no output schema, the description lacks information about the response (e.g., text output, confidence scores). The agent would need to infer or discover the return type from usage.

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?

Schema coverage is 100%, so both parameters have descriptions. The description adds no extra value beyond the schema, but baseline 3 is appropriate as the schema already documents parameters adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Send a simple query') and the target resource ('Perplexity AI'). It distinguishes from the sibling tool 'perplexity_chat' by implying this is for a single query, while 'chat' likely involves multi-turn conversation.

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?

No guidance is provided on when to use this tool versus the sibling 'perplexity_chat'. There is no mention of prerequisites, limitations, or alternatives, leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

perplexity_chatC

Generate a chat completion using Perplexity AI

ParametersJSON Schema
NameRequiredDescriptionDefault
modelNoThe model to use for completion
messagesYesArray of messages in the conversation
temperatureNoSampling temperature (0-2)

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No behavioral traits are disclosed beyond the minimal description. The schema includes a model with 'sonar-small-online' suggesting internet access, but this is not mentioned. With no annotations, the description should provide more context about side effects, permissions, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise, but it is too brief to convey necessary information. It could be expanded without losing conciseness.

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 tool has 3 parameters and a sibling tool, the description is insufficient. It does not explain the role of Perplexity AI, the meaning of different models, or how this tool differs from 'perplexity_ask'. The lack of output schema increases the need for a more complete description.

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?

Schema description coverage is 100%, so all parameters are documented in the schema. The description adds no additional meaning beyond what is already in the schema. Baseline score of 3 is appropriate.

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: generating a chat completion using Perplexity AI. However, it does not differentiate from the sibling tool 'perplexity_ask', which likely performs a similar but distinct function.

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 the sibling tool 'perplexity_ask'. The context hints at a distinction (chat vs. ask), but it is not explicitly stated.

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. 2 tool updatesv1.0.1
    • First observedperplexity_ask
    • First observedperplexity_chat
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

C2.9/5.0

Scored across 2 tools

Disambiguation2/5

Both tools involve querying Perplexity AI, with only subtle differences in description ('simple query' vs 'chat completion'). An agent would likely struggle to decide which to use, as the boundaries are unclear.

Naming Consistency4/5

Both tools follow a consistent 'perplexity_<verb>' pattern. The verbs 'ask' and 'chat' are different but semantically related, and no mixing of naming conventions is present.

Tool Count3/5

With only 2 tools, the server feels minimal for a service like Perplexity AI, which typically offers more nuanced capabilities (e.g., different models, streaming). However, it covers basic query and chat needs.

Completeness3/5

The tool surface covers basic query and chat interactions but lacks operations such as specifying model parameters, context handling, or result streaming. This may limit agent flexibility.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Perplexity MCP Server

    Family-IT-Guy
    A
    license
    Not graded
    quality
    F
    maintenance
    A custom Model Context Protocol implementation that integrates Perplexity AI with Claude Desktop, allowing users to access Perplexity's AI models for both single questions and multi-turn conversations.
    35 npm
    15
    ISC

  • Kagi MCP

    yuki-yano
    A
    license
    B
    quality
    D
    maintenance
    A Node.js implementation of the Kagi Model Context Protocol server that enables Claude AI to search the web and summarize documents, videos, and audio using Kagi's APIs.
    2
    18 npm
    MIT

Appeared in Searches