Skip to main content
Glama

fetch_json

Retrieve JSON data from any URL by specifying the endpoint and optional headers. Simplify API integration and data extraction for web content.

Instructions

Fetch a JSON file from a URL

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
headersNoOptional headers to include in the request
urlYesURL of the JSON to fetch

Implementation Reference

  • The static method `Fetcher.json` that executes the core logic of the `fetch_json` tool: fetches the JSON from the provided URL, parses it, stringifies it, and returns it in the expected MCP response format.
    static async json(requestPayload: RequestPayload) {
      try {
        const response = await this._fetch(requestPayload);
        const json = await response.json();
        return {
          content: [{ type: "text", text: JSON.stringify(json) }],
          isError: false,
        };
      } catch (error) {
        return {
          content: [{ type: "text", text: (error as Error).message }],
          isError: true,
        };
      }
  • src/index.ts:105-122 (registration)
    Registers the `fetch_json` tool in the `ListToolsRequestHandler` with its name, description, and input schema.
    {
      name: "fetch_json",
      description: "Fetch a JSON file from a URL",
      inputSchema: {
        type: "object",
        properties: {
          url: {
            type: "string",
            description: "URL of the JSON to fetch",
          },
          headers: {
            type: "object",
            description: "Optional headers to include in the request",
          },
        },
        required: ["url"],
      },
    },
  • Dispatches the `CallToolRequest` for `fetch_json` by calling `Fetcher.json` after validation.
    if (request.params.name === "fetch_json") {
      const fetchResult = await Fetcher.json(validatedArgs);
      return fetchResult;
  • Shared Zod schema `RequestPayloadSchema` used to validate the input arguments for the `fetch_json` tool (and others) in the `CallToolRequestHandler`.
    import { z } from "zod";
    
    export const RequestPayloadSchema = z.object({
      url: z.string().url(),
      headers: z.record(z.string()).optional(),
    });
    
    export type RequestPayload = z.infer<typeof RequestPayloadSchema>;
  • Private helper method `_fetch` used by `Fetcher.json` (and other methods) to perform the actual HTTP fetch with error handling and default User-Agent.
    private static async _fetch({
      url,
      headers,
    }: RequestPayload): Promise<Response> {
      try {
        const response = await fetch(url, {
          headers: {
            "User-Agent":
              "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
            ...headers,
          },
        });
    
        if (!response.ok) {
          throw new Error(`HTTP error: ${response.status}`);
        }
        return response;
      } catch (e: unknown) {
        if (e instanceof Error) {
          throw new Error(`Failed to fetch ${url}: ${e.message}`);
        } else {
          throw new Error(`Failed to fetch ${url}: Unknown error`);
        }
      }
Install Server

Other Tools

Related 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/tokenizin-agency/mcp-npx-fetch'

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