mcp-perplexity

daniel-lxs/mcp-perplexity

4.0

mcp-perplexity is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.

If you are the rightful owner of mcp-perplexity and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Perplexity MCP Server provides a Python-based interface to the Perplexity API, offering tools for querying responses, maintaining chat history, and managing conversations.

Try mcp-perplexity with chat:

MCPHub score:4.05

Has a README

Github repo has a README.md.

Has a License

Github repo has license info.

Server can be inspected

View server inspector

Server schema can be extracted

Can get at lease one tool info from the README or server.

Online hosted on MCPHub

Can be automatically deployed by MCPHub.

Has social accounts

Do not have any social accounts.

Claimed by the author or certified by MCPHub

If you are the author, claim authorship

AI Evaluation Report
Total Score: 9/10

The agent demonstrates strong capabilities in managing conversations with Perplexity AI, including creating new chats, retrieving chat histories, and providing detailed responses with source citations. The agent consistently provides accurate and comprehensive information, maintains the expected format for chat IDs, and includes relevant sources to enhance credibility. The agent's performance in handling programming-related queries and general information requests is robust, showcasing its ability to deliver expert-level assistance. However, the evaluation does not cover potential limitations in handling more complex or nuanced queries, which could be an area for further testing. Overall, the agent performs well within its defined capabilities.

  • Test case 1
    Score: 9/10
    Perform the operation of creating a new chat with Perplexity AI using the `chat_perplexity` tool, with the title 'Python Debugging Session' and the initial message 'How can I resolve a TypeError in Python when adding an integer to a string?'. Provide the chat ID for future reference.

    The chat has been successfully created with the title 'Python Debugging Session'. The Chat ID is proud-fog-03 for future reference.

  • Test case 2
    Score: 10/10
    Perform the operation of retrieving the complete conversation history for the chat with Chat ID 'proud-fog-03' using the `read_chat_perplexity` tool, and provide the full transcript of the conversation.

    Chat ID: proud-fog-03
    Title: Python Debugging Session
    Created: 2025-08-02 07:32:37 Messages:

    1. [2025-08-02 07:32:37] You:
      How can I resolve a TypeError in Python when adding an integer to a string?
    2. [2025-08-02 07:32:41] Assistant:
      You can resolve a TypeError in Python when adding an integer to a string by converting the integer to a string using the str() function before concatenation. For example:
      result = "Year is " + str(2023)
      print(result)  # Output: Year is 2023
      
      This error occurs because Python does not implicitly convert integers to strings when using the + operator for concatenation. Other ways to avoid this error include:
      • Using commas in the print() function, which automatically converts arguments to strings:
        print("Year is", 2023)  # Output: Year is 2023
        
      • Using formatted strings (f-strings) for clearer syntax:
        year = 2023
        print(f"Year is {year}")  # Output: Year is 2023
        
      • Using string formatting operators like %:
        print("%s%s" % ("Year is ", 2023))  # Output: Year is 2023
        
      In summary, always convert integers to strings explicitly with str() or use formatting methods to combine strings and integers safely. Sources:
      1. DigitalOcean
      2. LearnDataSci
      3. Real Python
      4. AccuWeb
      5. LabEx
  • Test case 3
    Score: 9/10
    Perform the operation of creating a new chat with Perplexity AI using the `chat_perplexity` tool, with the title 'Malcolm-Jamal Warner's Legacy' and the initial message 'Can you provide an overview of Malcolm-Jamal Warner's career and his impact on television and music?'. Provide the chat ID for future reference.

    The chat has been successfully created with the title "Malcolm-Jamal Warner's Legacy." The chat ID for future reference is autumn-field-72.

  • Test case 4
    Score: 9/10
    Perform the operation of creating a new chat with Perplexity AI using the `chat_perplexity` tool, with the title 'Virginia Giuffre's Family's Reaction to Trump's Comments' and the initial message 'What are the details surrounding Virginia Giuffre's family's reaction to President Trump's comments about Jeffrey Epstein 'stealing' her from Mar-a-Lago?'. Provide the chat ID for future reference.

    The chat has been successfully created with the following details: Chat ID: divine-cake-54

    Chat History:

    • User's Question: What are the details surrounding Virginia Giuffre's family's reaction to President Trump's comments about Jeffrey Epstein 'stealing' her from Mar-a-Lago?

    • Response: Virginia Giuffre's family reacted with outrage and rejection to President Donald Trump's comments suggesting that Epstein "stole" her from Mar-a-Lago. Trump claimed Giuffre, who worked at Mar-a-Lago in 2000, was one of several employees Epstein took, saying, "He stole her." The family clarified that Giuffre was not "stolen" by Epstein but was targeted and preyed upon by convicted sex trafficker Ghislaine Maxwell when Giuffre was 16, several years before Epstein and Trump had a falling out. They expressed shock at Trump's remarks and questioned whether he knew about Epstein and Maxwell's actions at the time. The family also urged Trump not to pardon Maxwell, emphasizing her role in trafficking Giuffre and other victims. This reaction highlights the family's insistence on accurately framing Giuffre's victimization as the result of deliberate targeting by Maxwell, rather than a casual "theft" by Epstein, and their concern about Trump's knowledge and comments on the matter.

    Sources:

    1. 6abc
    2. ABC News
    3. Democracy Now
    4. YouTube
    5. Global News Feel free to refer back to this chat using the provided Chat ID for any future inquiries!