Skip to main content
Glama

chaingpt_invoke_chat

Chat with a Web3 AI assistant to get blockchain insights, analyze crypto markets, and answer crypto-related questions using trained blockchain data and real-time information.

Instructions

    Invoke a chat with ChainGPT AI and get a response based on the provided question.
    Web3-native AI assistant built specifically for the crypto world. 
    It has deep blockchain expertise, enabling seamless integration of crypto-aware AI into your applications. 
    The model is trained on blockchain data (smart contracts, DeFi protocols, NFTs, DAOs) and real-time market information, 
    making it ideal for use cases like customer support, on-chain analytics, trading assistance, and community engagement

    Capabilities:
        - Aggregate any amount of web3 market statistics
        - Interact with Blockchains 
        - Live information tracking of 5,000+ cryptos.
        - AI Generated News

    ⚠️ COST WARNING: This tool makes an API call to ChainGPT which may incur costs.

    This tool allows you to interact with ChainGPT's conversational AI capabilities.

    Args:
        question (str): The question or message to send to ChainGPT.
        chatHistory (str, optional): Whether to include chat history in the request.
            Defaults to "off" if not provided. Can be set to "on" to maintain conversation context.
        sdkUniqueId (str, optional): The unique identifier for the chat.
            Defaults to a random UUID if not provided
    Returns:
        The response from ChainGPT AI to the provided question or message.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionYes
chatHistoryYes

Implementation Reference

  • The asynchronous handler function that executes the tool logic: calls ChainGPT's createChatBlob API with question and chatHistory, returns the bot response in MCP format, or an error message if failed.
    async (params) => {
      try {
        const response = await generalchat.createChatBlob({
          question: params.question,
          chatHistory: params.chatHistory,
        });
        return {
          content: [
            {
              type: "text",
              text: response.data.bot,
            },
          ],
        };
      } catch (error) {
        const errorMessage =
          error instanceof Error ? error.message : "invoke_chat_Unknown_Error";
        return {
          content: [
            {
              type: "text",
              text: errorMessage,
            },
          ],
          isError: true,
        };
      }
    }
  • Zod schema defining the input parameters for the chaingpt_invoke_chat tool: question (required string) and chatHistory (optional string).
    export const chatSchema = {
        question: z.string().min(1, 'Question is required'),
        chatHistory: z.string(),
    }
  • Registers the 'chaingpt_invoke_chat' tool on the MCP server, providing the tool name, detailed description, input schema, and handler function.
    server.tool(
      "chaingpt_invoke_chat",
      `
          Invoke a chat with ChainGPT AI and get a response based on the provided question.
          Web3-native AI assistant built specifically for the crypto world. 
          It has deep blockchain expertise, enabling seamless integration of crypto-aware AI into your applications. 
          The model is trained on blockchain data (smart contracts, DeFi protocols, NFTs, DAOs) and real-time market information, 
          making it ideal for use cases like customer support, on-chain analytics, trading assistance, and community engagement
    
          Capabilities:
              - Aggregate any amount of web3 market statistics
              - Interact with Blockchains 
              - Live information tracking of 5,000+ cryptos.
              - AI Generated News
    
          ⚠️ COST WARNING: This tool makes an API call to ChainGPT which may incur costs.
    
          This tool allows you to interact with ChainGPT's conversational AI capabilities.
    
          Args:
              question (str): The question or message to send to ChainGPT.
              chatHistory (str, optional): Whether to include chat history in the request.
                  Defaults to "off" if not provided. Can be set to "on" to maintain conversation context.
              sdkUniqueId (str, optional): The unique identifier for the chat.
                  Defaults to a random UUID if not provided
          Returns:
              The response from ChainGPT AI to the provided question or message.
          `,
      chatSchema,
      async (params) => {
        try {
          const response = await generalchat.createChatBlob({
            question: params.question,
            chatHistory: params.chatHistory,
          });
          return {
            content: [
              {
                type: "text",
                text: response.data.bot,
              },
            ],
          };
        } catch (error) {
          const errorMessage =
            error instanceof Error ? error.message : "invoke_chat_Unknown_Error";
          return {
            content: [
              {
                type: "text",
                text: errorMessage,
              },
            ],
            isError: true,
          };
        }
      }
    );
  • Initializes the GeneralChat SDK client instance used by the handler, configured with the ChainGPT API secret key from config.
    const generalchat = new GeneralChat({
      apiKey: config.chaingpt.secretKey,
    });
  • src/tools/index.ts:4-7 (registration)
    Top-level tool registration function that invokes registerChatTools(), which in turn registers the chaingpt_invoke_chat tool.
    export const registerTools = () => {
        registerChatTools();
        registerNewsTools();
    }

Tool Definition Quality

Score is being calculated. Check back soon.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mikeysrecipes/chaingpt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server