MCP Perplexity

@daniel-lxs

代码仓库

基本信息

分类

AI 与智能体

许可证

MIT

传输方式

stdio

作者

daniel-lxs

提交者

Yunkun Han

关于 MCP Perplexity

MCP Server for the Perplexity API.

#mcp-perplexity#perplexity-api #chat-server

MCP Perplexity 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-perplexity": {
      "command": "uvx",
      "args": [
        "mcp-perplexity"
      ],
      "env": {
        "PERPLEXITY_API_KEY": "your-api-key",
        "PERPLEXITY_MODEL": "sonar-pro",
        "DB_PATH": "chats.db"
      }
    }
  }
}

MCP Perplexity 工具

Provides expert programming assistance through Perplexity. This tool only has access to the context you have provided. It cannot read any file unless you provide it with the file content. Focuses on coding solutions, error debugging, and technical explanations. Returns responses with source citations and alternative suggestions.

Maintains ongoing conversations with Perplexity AI. Creates new chats or continues existing ones with full history context. This tool only has access to the context you have provided. It cannot read any file unless you provide it with the file content. Returns chat ID for future continuation. For new chats: Provide 'message' and 'title' For existing chats: Provide 'chat_id' and 'message'

Lists all available chat conversations with Perplexity AI. Returns chat IDs, titles, and creation dates. Results are paginated with 50 chats per page.

Retrieves the complete conversation history for a specific chat. Returns the full chat history with all messages and their timestamps. No API calls are made to Perplexity - this only reads from local storage.

概览

What is Mcp Perplexity?

Mcp Perplexity is a Python-based MCP server that provides a programmatic interface to the Perplexity API. It offers tools for querying responses, maintaining chat history, and managing conversations, mimicking the browser-based Perplexity Chat experience. Designed for developers, it integrates with MCP-compatible clients and stores chat data locally.

How to use Mcp Perplexity?

Configure your MCP client with the command uvx mcp-perplexity and set the required environment variable PERPLEXITY_API_KEY. Optionally set PERPLEXITY_MODEL, DB_PATH, and other variables. You can also use Smithery CLI: npx -y @smithery/cli@latest run @daniel-lxs/mcp-perplexity --config "{\"perplexityApiKey\":\"pplx-abc\",\"perplexityModel\":\"sonar-pro\"}".

Key features of Mcp Perplexity

Model selection via PERPLEXITY_MODEL environment variable.
Separate models for ask and chat tools.
Persistent chat history with local database storage.
Streaming responses with progress reporting to prevent timeouts.
Paginated chat listing (50 chats per page, relative timestamps).
Optional web UI for interactive chat management.

Use cases of Mcp Perplexity

Ask specific programming questions and receive source citations.
Maintain ongoing, context-aware conversations with Perplexity AI.
List and review all previous chat conversations.
Debug and research using full chat history retrieval.
Integrate Perplexity’s capabilities into development workflows.

常见问题

What Python version is required?

Python 3.10 or higher is required.

How do I set my Perplexity API key?

Set the environment variable `PERPLEXITY_API_KEY` in your MCP client configuration. It is required.

Can I use different models for ask and chat tools?

Yes, set `PERPLEXITY_MODEL_ASK` for `ask_perplexity` and `PERPLEXITY_MODEL_CHAT` for `chat_perplexity`. These override the default `PERPLEXITY_MODEL`.

Where is chat history stored?

Chat history is stored locally in a SQLite database at the path specified by `DB_PATH` (default: `chats.db`). The `read_chat_perplexity` tool reads from this local storage without making API calls.

Is there a web interface?

Yes, when `WEB_UI_ENABLED` is set to `true`, a web UI is available at `http://WEB_UI_HOST:WEB_UI_PORT` (default `http://127.0.0.1:8050`).

AI 与智能体分类下的更多 MCP 服务器

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

Poker Bots All Stars

Agent Disco

Live Texas Hold'em for AI agents: your assistant plays your 3D star, talks trash, anyone can watch.

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g