AI Humanizer MCP Server

Instructions

Implementation Reference

• src/index.ts:95-125 (handler)

  Handler for the 'detect' tool: parses input arguments using Zod schema, sends POST request to AI detection API endpoint, handles response or error, and returns JSON stringified result.

  if (name === "detect") {
    const argument = AiDetectArgumentSchema.parse(args);
  
    const detectUrl = `${API_BASE}/rewrite/text-detection`;
    const detectData = await makeRequest<AiDetectResponse>(detectUrl, argument);
  
    if (!detectData) {
      return {
        content: [
          {
            type: "text",
            text: "Failed to retrieve alerts data",
          },
        ],
      };
    }
  
    const responseData = {
      ...detectData
      ,text: undefined,
    };
  
    return {
      content: [
        {
          type: "text",
          text: JSON.stringify(responseData),
        },
      ],
    };
  } else {

• src/index.ts:35-64 (registration)

  Registration of the 'detect' tool in the ListToolsRequestSchema handler, defining name, description, and JSON input schema.

  server.setRequestHandler(ListToolsRequestSchema, async () => {
    return {
      tools: [
          {
              name: "detect",
              description: "Detect whether the text is AI-generated.Show to user the task detail url. Extract the taskId field, then concatenate the link in the following format: https://pre-www.text2go.ai/?utm_source=claude_mcp&taskId={taskId}",
              inputSchema: {
                type: "object",
                properties: {
                  type: {
                    type: "string",
                    enum: ["original_text"],
                  },
                  text: {
                    type: "string",
                  },
                  detectionTypeList: {
                    type: "array",
                    items: {
                      type: "string",
                      enum: ["COPYLEAKS", "HEMINGWAY"],
                    },
                  },
                },
                required: ["type", "text", "detectionTypeList"],
              },
            }
      ],
    };
  });

• src/index.ts:13-21 (schema)

  Zod schema (AiDetectArgumentSchema) for validating and parsing the input arguments to the 'detect' tool handler.

  const AiDetectArgumentSchema = z
    .object({
      type: z.enum(["original_text"]),
      text: z.string(),
      detectionTypeList: z.array(
        z.enum(["COPYLEAKS", "HEMINGWAY"])
      ),
    })
    .required();

• src/index.ts:66-88 (helper)

  Helper function 'makeRequest' used by the 'detect' handler to perform POST requests to the external API.

  async function makeRequest<T>(url: string, data?: any): Promise<T | null> {
    const headers = {
      "User-Agent": USER_AGENT,
      "Accept": "application/json",
      "Content-Type": "application/json"
    };
  
    try {
      const response = await fetch(url, {
        method: 'POST',
        headers,
        body: data ? JSON.stringify(data) : undefined
      });
      
      if (!response.ok) {
        throw new Error(`HTTP error! status: ${response.status}`);
      }
      return (await response.json()) as T;
    } catch (error) {
      console.error("Error making request:", error);
      return null;
    }
  }