How We Built a Remote 10-Tool Streamable HTTP MCP Server and 13.3 KiB Link-in-Bio in Go A developer built Linq.es, a link-in-bio platform whose public pages ship 13.3 KiB of gzipped first-party CSS and JS with no SPA framework, alongside a remote MCP server at https://linq.es/mcp that exposes 10 tools over Streamable HTTP (JSON-RPC 2.0, MCP spec 2025-03-26) with bearer-token auth and no local npx or stdio wrapper. The writeup details two Go/Gin implementation lessons: returning 202 Accepted with an empty body for JSON-RPC notifications that omit the id field, and running storage and CDN cache purges inside a sync.WaitGroup before responding to tools/call so serverless CPU throttling doesn't leave stale pages. Public link-in-bio pages are structurally simple documents: an avatar, a name, a contact bar, and 5 to 20 links. Yet most commercial bio-link platforms render them as client-heavy Single-Page Applications that download hundreds of kilobytes of framework JavaScript inside Instagram, TikTok, or WhatsApp in-app WebViews before painting a button. When we built Linq.es https://linq.es and its Official Remote MCP Server https://linq.es/mcp https://linq.es/integrations/mcp , we took the opposite path on both the public frontend and the AI agent layer: html/template 5.1 KiB of gzipped async CSS, 8.2 KiB of gzipped defer vanilla JS, and zero React, Next.js, or Vue runtime 13.3 KiB total gzipped first-party CSS + JS . https://linq.es/mcp over Streamable HTTP JSON-RPC 2.0 , MCP spec 2025-03-26 lnq live ... , without installing a local npx or Python stdio wrapper. Below are the main architectural lessons we learned building both layers in Go. Most link-in-bio clicks happen inside constrained mobile WebViews Instagram, TikTok, LinkedIn, X, and WhatsApp over variable cellular connections. Every extra script tag, font round-trip, and client hydration pass delays First Contentful Paint and increases bounce rates before a visitor taps a wa.me button or downloads a .vcf contact card. On Linq.es, public profiles render complete semantic HTML in the European Union behind a multi-tier cache in-memory L1, persistent object storage L2, and Cloudflare Edge CDN : Async stylesheet: ~5.1 KiB gzipped loaded non-blocking Deferred vanilla JS: ~8.2 KiB gzipped loaded with defer Total external CSS+JS: 13.3 KiB gzipped zero client SPA framework No third-party ad pixels Meta, TikTok, or GA4 are injected on public pages unless a Pro profile owner explicitly configures their own measurement IDs. Many early MCP integrations wrap an existing REST API inside a local Node.js stdio package that users run via npx -y @vendor/mcp-server . That introduces three recurring friction points: With the 2025-03-26 Streamable HTTP specification, an MCP server runs as a standard HTTPS JSON-RPC 2.0 endpoint: GET https://linq.es/mcp serves human-readable discovery metadata name: "linqes-mcp" , protocolVersion: "2025-03-26" , transport: "streamable-http" . POST https://linq.es/mcp handles initialize , notifications/initialized , ping , tools/list , and authenticated tools/call executions. 202 Accepted with an empty body During the MCP handshake, right after initialize succeeds, strict clients send a JSON-RPC notification {"jsonrpc": "2.0", "method": "notifications/initialized"} that omits the id field. If your HTTP router wraps every return path in a 200 OK JSON-RPC envelope with "id": null , strict clients treat the unexpected body as a protocol error. In Go + Gin, handling JSON-RPC notifications before dispatching methods keeps the handshake clean: // JSON-RPC notifications omit "id" and must not return a JSON-RPC response body. if strings.HasPrefix req.Method, "notifications/" || len req.ID == 0 { c.Status http.StatusAccepted return } On serverless container platforms, CPU allocation drops as soon as the HTTP response finishes writing. If an AI agent calls add profile link or update profile link and you trigger CDN cache purges in detached background goroutines, the container can be throttled before the outbound purge completes, leaving visitors looking at stale HTML when the agent reports the link is live. Running storage and CDN cache invalidations concurrently inside a sync.WaitGroup before returning the tools/call response guarantees that by the time Claude or Cursor replies "Done, live at https://linq.es/handle" , public visitors already see the updated page: js var wg sync.WaitGroup wg.Add 2 go func { defer wg.Done purgeObjectCache ctx, profileHandle } go func { defer wg.Done purgeEdgeCDN ctx, profileHandle } wg.Wait When exposing read, write, and delete operations side by side, tool descriptions alone should not force an LLM host to guess which calls are safe to auto-approve and which require human confirmation. Adding standard MCP annotations readOnlyHint , destructiveHint , idempotentHint , and openWorldHint using explicit boolean pointers in Go ensures false values serialize cleanly instead of being dropped by omitempty : type MCPToolAnnotations struct { Title string json:"title,omitempty" ReadOnlyHint bool json:"readOnlyHint,omitempty" DestructiveHint bool json:"destructiveHint,omitempty" IdempotentHint bool json:"idempotentHint,omitempty" OpenWorldHint bool json:"openWorldHint,omitempty" } Combined with "additionalProperties": false on every tool's inputSchema and clear prerequisite notes e.g., calling list profiles to discover handles and list profile links before update profile link or delete profile link , agents avoid hallucinating parameters or accidentally deleting links when a user only asked to hide one active: false . Once you generate a Personal API Key in Account Settings, you can connect Cursor ~/.cursor/mcp.json , Claude Desktop, Windsurf, or Gemini CLI ~/.gemini/settings.json directly over HTTPS: { "mcpServers": { "linqes": { "url": "https://linq.es/mcp", "headers": { "Authorization": "Bearer lnq live YOUR PERSONAL API KEY" } } } } From there, your agent can use all 10 tools across up to 5 profiles and 500 /s/ shortlinks: list profiles : List owned profiles, themes, public URLs, and cumulative view counts. get profile analytics : Pull 1-to-90-day views, clicks, CTR percentage, referrers, countries, devices, and daily time series. list profile links : Inspect every link's key , url , active state, click count, and iOS/Android overrides. add profile link : Publish a link or social icon with optional badgeText , iosUrl , androidUrl , scheduleStart / scheduleEnd RFC3339 , live countdown, or click badge. update profile link & delete profile link : Edit, toggle active: false , or permanently remove links with immediate cache invalidation. import bio links : Migrate public links from an existing Linktree, Beacons, or Bio.link URL in one call. list shortlinks & create shortlink : Create and audit https://linq.es/s/:code shortlinks with custom 3-50 character slugs, iOS/Android routing, and utm source through utm content tags. list leads : Retrieve recent Name, Email, and WhatsApp contacts captured via your profile's Lead Magnet form. You can inspect the live discovery metadata anytime with curl -s https://linq.es/mcp | jq . , try the free .vcf , WhatsApp, and UTM generators without an account at https://linq.es/tools https://linq.es/tools , or read the full MCP setup docs at https://linq.es/integrations/mcp https://linq.es/integrations/mcp .