Provides access to Perplexity2 API for searching and analyzing Google data using AI to organize information and extract insights.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Perplexity2 MCP Server search for the latest AI research papers on large language models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
用于访问 Perplexity2 API 的 MCP 服务器。
EMCP 是一个强大的 MCP 服务器管理平台，让您无需手动配置即可快速使用各种 MCP 服务器！
🌐 访问 EMCP 平台
📝 注册并登录账号
🎯 进入 MCP 广场，浏览所有可用的 MCP 服务器
🔍 搜索或找到本服务器（bach-perplexity2）
🎉 点击 "安装 MCP" 按钮
✅ 完成！即可在您的应用中使用
✨ 零配置：无需手动编辑配置文件
🎨 可视化管理：图形界面轻松管理所有 MCP 服务器
🔐 安全可靠：统一管理 API 密钥和认证信息
🚀 一键安装：MCP 广场提供丰富的服务器选择
📊 使用统计：实时查看服务调用情况
立即访问 EMCP 平台 开始您的 MCP 之旅！
Related MCP server: Perplexity MCP Server
这是一个 MCP 服务器，用于访问 Perplexity2 API。
PyPI 包名: bach-perplexity2
版本: 1.0.0
传输协议: stdio
pip install bach-perplexity2pip install -e .# 运行（uvx 会自动安装并运行）
uvx --from bach-perplexity2 bach_perplexity2
# 或指定版本
uvx --from bach-perplexity2@latest bach_perplexity2python server.py# 安装
pip install bach-perplexity2
# 运行（命令名使用下划线）
bach_perplexity2此 API 需要认证。请设置环境变量:
export API_KEY="your_api_key_here"变量名 | 说明 | 必需 |
| API 密钥 | 是 |
| 不适用 | 否 |
| 不适用 | 否 |
编辑 Cursor MCP 配置文件 ~/.cursor/mcp.json:
{
"mcpServers": {
"bach-perplexity2": {
"command": "uvx",
"args": ["--from", "bach-perplexity2", "bach_perplexity2"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}编辑 Claude Desktop 配置文件 claude_desktop_config.json:
{
"mcpServers": {
"bach-perplexity2": {
"command": "uvx",
"args": ["--from", "bach-perplexity2", "bach_perplexity2"],
"env": {
"API_KEY": "your_api_key_here"
}
}
}
}此服务器提供以下工具:
postDiscover the power of data with our API, designed to search Google data effortlessly. Leverage AI to analyze and organize information, unlocking insights and enhancing your decision-making capabilities.
端点: POST /
传输协议: stdio
HTTP 客户端: httpx
MIT License - 详见 LICENSE 文件。
此服务器由 API-to-MCP 工具生成。
版本: 1.0.0
Discover the power of data with our API, designed to search Google data effortlessly. Leverage AI to analyze and organize information, unlocking insights and enhancing your decision-making capabilities.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral information. With no annotations, the description carries full burden but doesn't disclose whether this is a read or write operation, what resources it affects, authentication requirements, rate limits, or expected behavior. The vague 'search Google data' hint contradicts the tool name 'post' (which typically implies creation/submission), creating confusion rather than transparency.
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 inefficiently structured with marketing fluff that doesn't serve the tool's documentation purpose. Sentences like 'Discover the power of data with our API' and 'unlocking insights and enhancing your decision-making capabilities' waste space without providing functional information. It's not appropriately front-loaded with essential details about what the tool actually does.
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?
The description is completely inadequate for understanding this tool. With no annotations, no output schema, and a misleading description that doesn't explain the tool's function, an agent cannot determine when or how to use this tool. The complexity of a 'post' operation (typically involving data submission) requires clear behavioral disclosure that's entirely missing.
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 tool has zero parameters with 100% schema description coverage, so the baseline is 4. The description doesn't need to compensate for any parameter gaps since there are none. While the description doesn't discuss parameters (because there aren't any), this doesn't detract from the parameter semantics dimension given the empty 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 fails to state what the tool does. It provides generic marketing language about 'discovering the power of data' and 'leveraging AI to analyze and organize information' but doesn't specify what action this 'post' tool performs. There's no verb+resource combination, no indication of whether it creates, updates, searches, or processes something. This is essentially misleading since it doesn't describe the tool's actual function.
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?
No guidance is provided on when to use this tool. The description mentions 'search Google data' but doesn't clarify if this is the tool's purpose or just general API capability. With no sibling tools, differentiation isn't needed, but there's still no indication of appropriate contexts, prerequisites, or limitations for using this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or overlap with other tools. The single tool 'post' stands alone with a distinct purpose, eliminating any risk of misselection.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'post' follows a simple verb pattern, and no inconsistencies can exist in a set of one.
A single tool is too few for a server named 'Perplexity2 MCP Server' with a description focused on data discovery, AI analysis, and Google search. This suggests a broader scope that would typically require multiple tools (e.g., for search, analysis, organization), making the count inappropriate and likely incomplete.
The server's description implies capabilities like searching Google data, AI analysis, and organizing information, but only a generic 'post' tool is provided. This is severely incomplete, lacking specific tools for search, retrieval, analysis, or other core functions, which will cause agent failures in handling the intended domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real-time web search, reasoning, and research through Perplexity's API
Enable AI assistants to perform web searches using Perplexity's Sonar Pro.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
1 Google Search endpoints. Pay per call in USDC via x402.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/BACH-AI-Tools/bachai-perplexity2'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
