Skip to main content
Glama
DeanWard

HAL (HTTP API Layer)

http-get

Send HTTP GET requests to specified URLs with customizable headers. Supports secret substitution using environment variables for secure API interactions within HAL (HTTP API Layer).

Instructions

Make an HTTP GET request to a specified URL. Supports secret substitution using {secrets.key} syntax where 'key' corresponds to HAL_SECRET_KEY environment variables.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
headersNo
urlYes

Implementation Reference

  • src/index.ts:571-584 (registration)
    Registration of the "http-get" MCP tool, including title, description, Zod input schema, and inline handler function that delegates to the shared makeHttpRequest helper.
    server.registerTool( "http-get", { title: "HTTP GET Request", description: "Make an HTTP GET request to a specified URL. Supports secret substitution using {secrets.key} syntax where 'key' corresponds to HAL_SECRET_KEY environment variables.", inputSchema: { url: z.string().url(), headers: z.record(z.string()).optional() } }, async ({ url, headers = {} }: { url: string; headers?: Record<string, string> }) => { return makeHttpRequest('GET', url, { headers }); } );
  • Zod input schema definition for the http-get tool: requires a valid URL string, optional headers as record of strings.
    inputSchema: { url: z.string().url(), headers: z.record(z.string()).optional() }
  • The registered handler function for http-get tool, which calls the shared makeHttpRequest function with GET method.
    async ({ url, headers = {} }: { url: string; headers?: Record<string, string> }) => { return makeHttpRequest('GET', url, { headers }); }
  • Core helper function implementing HTTP request logic shared across all http-* tools: performs secret substitution in inputs using substituteSecrets, validates URL against whitelist/blacklist/environment restrictions, executes fetch request, processes response (pretty-prints JSON, handles HEAD), redacts secrets from response content and headers before returning.
    async function makeHttpRequest( method: string, url: string, options: { headers?: Record<string, string>; body?: string; queryParams?: Record<string, any>; } = {} ) { try { const { headers = {}, body, queryParams = {} } = options; // First, substitute secrets in URL to get the final URL for validation // We need to do this in two passes to handle URL restrictions properly const processedUrl = substituteSecrets(url, url); // Now substitute secrets in headers, body, and query parameters using the processed URL const processedHeaders = substituteSecretsInObject(headers, processedUrl); const processedBody = body ? substituteSecrets(body, processedUrl) : body; const processedQueryParams = substituteSecretsInObject(queryParams, processedUrl); // Build URL with query parameters const urlObj = new URL(processedUrl); Object.entries(processedQueryParams).forEach(([key, value]) => { if (value !== undefined && value !== null) { urlObj.searchParams.set(key, String(value)); } }); const finalUrl = urlObj.toString(); // Check global URL whitelist/blacklist const urlCheck = isUrlAllowedGlobal(finalUrl); if (!urlCheck.allowed) { throw new Error(urlCheck.reason || 'URL is not allowed'); } const defaultHeaders = { 'User-Agent': 'HAL-MCP/1.0.0', ...processedHeaders }; // Add Content-Type for methods that typically send data if (['POST', 'PUT', 'PATCH'].includes(method.toUpperCase()) && processedBody && !('Content-Type' in processedHeaders)) { (defaultHeaders as any)['Content-Type'] = 'application/json'; } const response = await fetch(finalUrl, { method: method.toUpperCase(), headers: defaultHeaders, body: processedBody }); const contentType = response.headers.get('content-type') || 'text/plain'; let content: string; // HEAD requests don't have a body by design if (method.toUpperCase() === 'HEAD') { content = '(No body - HEAD request)'; } else { try { if (contentType.includes('application/json')) { const text = await response.text(); if (text.trim()) { content = JSON.stringify(JSON.parse(text), null, 2); } else { content = '(Empty response)'; } } else { content = await response.text(); } } catch (parseError) { // If JSON parsing fails, try to get text try { content = await response.text(); } catch (textError) { content = '(Unable to parse response)'; } } } // Redact secrets from response headers and content before returning const redactedHeaders = Array.from(response.headers.entries()) .map(([key, value]) => `${key}: ${redactSecretsFromText(value)}`) .join('\n'); const redactedContent = redactSecretsFromText(content); return { content: [{ type: "text" as const, text: `Status: ${response.status} ${response.statusText}\n\nHeaders:\n${redactedHeaders}\n\nBody:\n${redactedContent}` }] }; } catch (error) { const errorMessage = error instanceof Error ? error.message : 'Unknown error'; const redactedErrorMessage = redactSecretsFromText(errorMessage); return { content: [{ type: "text" as const, text: `Error making ${method.toUpperCase()} request: ${redactedErrorMessage}` }], isError: true }; } }

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/DeanWard/HAL'

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