Skip to main content
Glama
Decodo

Decodo MCP Server

chatgpt

Read-only

Send prompts to ChatGPT with optional web search and geolocation settings to get AI-powered responses tailored to specific regions.

Instructions

Search and interact with ChatGPT for AI-powered responses and conversations

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesPrompt to send to ChatGPT
searchNoActivates ChatGPT's web search functionality
geoNoGeolocation of the desired request, expressed as a country name

Implementation Reference

  • ChatGPTTool class: contains the full handler logic. The register() method (line 15-51) defines the 'chatgpt' tool with input schema, calls sapiClient.scrape() with target SCRAPER_API_TARGETS.CHATGPT, and transforms the response.
    export class ChatGPTTool extends Tool {
      toolset = TOOLSET.AI;
    
      transformResponse = ({ data }: { data: object }) => {
        return { data: JSON.stringify(data, null, 2) };
      };
    
      register = ({ server, sapiClient, auth }: ToolRegistrationArgs) => {
        server.registerTool(
          'chatgpt',
          {
            description: 'Search and interact with ChatGPT for AI-powered responses and conversations',
            inputSchema: {
              prompt: z.string().describe('Prompt to send to ChatGPT'),
              search: z.boolean().describe("Activates ChatGPT's web search functionality").optional(),
              geo: zodGeo,
            },
            annotations: {
              readOnlyHint: true,
              openWorldHint: true,
            },
          },
          async (scrapingParams: ScrapingMCPParams, extra: ProgressExtra) => {
            const params = {
              ...scrapingParams,
              target: SCRAPER_API_TARGETS.CHATGPT,
              parse: true,
            } satisfies ScraperAPIParams;
    
            const { data } = await sapiClient.scrape<object>({ auth, scrapingParams: params, extra });
    
            const { data: text } = this.transformResponse({ data });
    
            return {
              content: [
                {
                  type: 'text',
                  text,
                },
              ],
            };
          }
        );
      };
    }
  • Input schema for the chatgpt tool: prompt (string), search (optional boolean), geo (optional string from zodGeo). Annotations: readOnlyHint, openWorldHint.
    {
      description: 'Search and interact with ChatGPT for AI-powered responses and conversations',
      inputSchema: {
        prompt: z.string().describe('Prompt to send to ChatGPT'),
        search: z.boolean().describe("Activates ChatGPT's web search functionality").optional(),
        geo: zodGeo,
      },
      annotations: {
        readOnlyHint: true,
        openWorldHint: true,
      },
    },
  • Registration of ChatGPTTool in the static allTools array on the server. ChatGPTTool is instantiated at line 95 and registered via the registerTools/registerAllTools flow.
      new ChatGPTTool(),
      new PerplexityTool(),
    ];
  • src/tools/index.ts:7-7 (registration)
    Barrel export re-exporting the chatgpt tool module from src/tools/chatgpt.
    export * from './chatgpt';
  • zodGeo helper schema used in the chatgpt tool input: an optional string describing geolocation as a country name.
    export const zodGeo = z
      .string()
      .describe('Geolocation of the desired request, expressed as a country name')
      .optional();
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds 'AI-powered responses and conversations' but does not disclose additional behavioral traits such as response format or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, appropriately concise, but it lacks structure and could benefit from front-loading key details like the use of search and geo parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has three parameters and no output schema, the description is too brief. It does not explain the openWorldHint, how to effectively use search and geo, or what kind of responses to expect, missing opportunities to compensate for the lack of output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no information beyond what is already in the schema for the parameters prompt, search, and geo.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool is for searching and interacting with ChatGPT for AI-powered responses, but it does not differentiate it from sibling tools like google_ai_mode or perplexity which serve similar purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like google_ai_mode or other search tools. The description does not mention conditions or contexts where ChatGPT is preferred.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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/Decodo/mcp-server'

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