MCP server exposing WebWeaver Nexus services (waitlist signup with embedded MCP App UI, product overview, contact info) to external AI hosts over Streamable HTTP.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
- !Install pipes a remote script into a shell (curl | sh)
claude mcp add webweaver -- npx -y cloudflared{
"mcpServers": {
"webweaver": {
"command": "npx",
"args": ["-y", "cloudflared"]
}
}
}MCP Servers overview
# WebWeaver Nexus MCP Server
An MCP server that exposes WebWeaver Nexus services — waitlist signup (with an embedded form UI), product overview, and contact info — to MCP-enabled hosts (Claude Desktop, claude.ai, ChatGPT, Cursor, MCP Inspector, basic-host).
**Production URL:** `https://webweaver-nexus-mcp.vercel.app/mcp` — Streamable HTTP, public, no authentication.
[](https://registry.modelcontextprotocol.io/?q=io.github.webweaver-nexus)
Published to the official MCP registry as `io.github.webweaver-nexus/webweaver-mcp-server`. See [Publishing to the MCP registry](#publishing-to-the-mcp-registry).
## Tools
| Tool | Type | Description |
|------|------|-------------|
| `join_waitlist` | MCP App (UI) | Embeds the Tally waitlist form inside the host |
| `get_product_overview` | Plain tool | Returns a description of what WebWeaver Nexus does |
| `get_contact_info` | Plain tool | Returns contact methods and links |
## Prerequisites
- Node.js 24.x (see `engines` in `package.json`)
- npm
> `engines` pins 24.x deliberately: Vercel selects the function runtime from it. Newer local Node majors work fine but make npm print an `EBADENGINE` warning.
## Install
```bash
npm install
```
## Build
```bash
npm run build
```
This bundles the MCP App UI with Vite + `vite-plugin-singlefile`, type-checks the client and server, and emits the compiled server.
The Vite step runs **first** and is load-bearing: a build plugin writes the bundled HTML into `generated/mcp-app-html.ts`, which `server.ts` imports. The server type-check would fail without it. `generated/` is a build artifact and is git-ignored.
> During `npm run dev`, the watch build regenerates that module on every client change, but `npm run serve` loads it once at startup — restart the server to pick up UI edits.
## Run
```bash
# HTTP transport (default, port 3001)
npm run serve
# Custom port
PORT=4000 npm run serve
# stdio transport (for Claude Desktop local config)
npm run serve:stdio
# Dev mode (watch + serve)
npm run dev
```
The server listens at `http://localhost:3001/mcp` by default.
## Configuration
Before deploying, update the Tally form ID:
1. Open `src/mcp-app.ts`
2. Replace the form ID constant with your real Tally form ID
3. Also update the `data-tally-src` URL in `mcp-app.html` to match
Tally's `embed.js` does **not** populate embeds by itself — `src/mcp-app.ts` has to call `window.Tally.loadEmbeds()` once the script loads, or the iframe keeps its `data-tally-src`, never gets a `src`, and the form silently renders as blank space.
Two settings keep the form readable in dark hosts and should be changed together: `transparentBackground=0` in the `data-tally-src` URL, and `color-scheme: light` on `#tally-container` in `src/mcp-app.css`. Tally's form styling does not follow the host theme, so with a transparent background its labels and inputs end up dark-on-dark. This mirrors the fix applied to the landing page embed.
## Testing with MCP Inspector (default harness)
[MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) is the official MCP debugger and the right tool for almost every check here. Verified against **v2.5.0**.
```bash
npx @modelcontextprotocol/inspector
```
The web UI opens on port `6274`. Set:
- **Transport Type:** `Streamable HTTP`
- **Connection Type:** `Via Proxy` or `Direct` — both work. Proxy routes JSON-RPC through Inspector's local proxy (port `6277`); Direct goes browser → server.
- **URL:** `http://localhost:3001/mcp` (local) or `https://webweaver-nexus-mcp.vercel.app/mcp` (production)
Click **Connect**, then verify across tabs:
1. **Tools** — all 3 tools appear (`join_waitlist`, `get_product_overview`, `get_contact_info`); the two plain tools return their text when called.
2. **Resources** — `ui://join-waitlist/mcp-app.html` lists; reading it returns ~435 KB of bundled HTML.
3. **Apps** — select `join_waitlist`; the Tally form renders inside its sandboxed iframe. Inspector builds a real CSP from our `_meta.ui.csp`, so this genuinely exercises `resourceDomains` / `frameDomains` / `connectDomains`. The form **renders** here but is **not fully interactive** — see [Inspector strips `allow-same-origin`](#mcp-inspector-strips-allow-same-origin) below.
There is also a CLI, which makes post-deploy checks scriptable without a browser:
```bash
npx @modelcontextprotocol/inspector --cli --transport http \
--server-url https://webweaver-nexus-mcp.vercel.app/mcp --method tools/list
# App metadata for a UI tool
npx @modelcontextprotocol/inspector --cli --transport http \
--server-url https://webweaver-nexus-mcp.vercel.app/mcp \
--method tools/call --tool-name join_waitlist --app-info
```
**The one thing Inspector cannot do:** accept `ui/update-model-context`. As of v2.5.0 it never registers an `onupdatemodelcontext` handler and never declares the capability, so `app.updateModelContext()` has nowhere to land. Use basic-host for that one check.
## Testing with basic-host (model context updates)
A vendored copy of the MCP Apps `basic-host` harness lives in [`tools/basic-host/`](tools/basic-host/). It is the only local host that declares the `updateModelContext` capability and renders a 📋 **Model Context** panel, which is how you confirm the waitlist form actually notifies the host model after submission.
```bash
# once
cd tools/basic-host && npm install && npm run build
# Terminal 1 — the server under test
npm run build && npm run serve
# Terminal 2 — the harness
cd tools/basic-host && SERVERS='["http://localhost:3001/mcp"]' npm run serve
# Open http://localhost:8080
```
Against production instead:
```bash
cd tools/basic-host && SERVERS='["https://webweaver-nexus-mcp.vercel.app/mcp"]' npm run serve
```
`SERVERS` is a **JSON array**, and ports 8080/8081 are effectively fixed — see [`tools/basic-host/README.md`](tools/basic-host/README.md) for provenance and the full set of caveats.
> The Model Context panel stays hidden until the first update arrives, which for `join_waitlist` means a **real Tally submission** — it creates a live waitlist entry and fires notification emails. Use a throwaway entry.
## When to use which
| Need | Use |
|------|-----|
| "Is the server reachable? Do tools list?" | Inspector (`--cli` for scripts) |
| "Do the plain tools return the right text?" | Inspector |
| "Does the Tally form render inside the CSP sandbox?" | Inspector (renders, but not fully interactive) |
| "Can a user actually complete and submit the form?" | basic-host or the deployed site |
| "Does `app.updateModelContext()` reach the host?" | basic-host — Inspector cannot |
| Fastest post-deploy sanity check | Inspector `--cli` |
## Exposing local dev to claude.ai (Cloudflare tunnel)
For iterating on the server locally against claude.ai's custom connector UI (which only accepts public HTTPS URLs, not `localhost`), expose your dev server via a Cloudflare tunnel:
```bash
# Terminal 1 — run the server
npm run build && npm run serve
# Terminal 2 — start the tunnel
npx cloudflared tunnel --url http://localhost:3001
```
Copy the `https://*.trycloudflare.com` URL from the tunnel output. In Claude's settings, add a custom MCP connector pointing to `https://<tunnel-url>/mcp`.
`*.trycloudflare.com` is allowlisted by the Host header check in `api/mcp.ts` — cloudflared forwards the public hostname rather than `localhost`, so without that entry every tunnelled request is rejected with `403 Invalid Host`.
> **Note:** As of writing, claude.ai's custom connectors ignore `frameDomains` declared in `_meta.ui.csp` (see [GitHub issue `anthropics/claude-ai-mcp#40`](https://github.com/anthropics/claude-ai-mcp/issues/40)). This will cause the Tally embed in `join_waitlist` to be blocked. The two read-only tools work correctly. Track that issue for the fix.
## Deployment (Vercel)
The MCP server is deployed as a Vercel serverless function using the Express + Streamable HTTP pattern.
**How it works:**
- `vercel.json` routes traffic to `api/mcp.ts`, which exports the Express app as `default`.
- The Vite-bundled MCP App UI is compiled into the function as a string constant (`generated/mcp-app-html.ts`), so no file is read from disk at runtime.
- The function runs on Vercel's Node.js 24 runtime with `maxDuration: 60` (well above what's needed; tool calls return in milliseconds).
- No environment variables are required — all configuration is hardcoded in the source.
**To redeploy:** Push to the `main` branch. Vercel auto-deploys on push.
**To verify the deployment:**
```bash
# Sanity check — should return a JSON-RPC tools list (~880 bytes)
curl -X POST https://webweaver-nexus-mcp.vercel.app/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
# Resource read — should return ~435 KB of bundled HTML.
# A response under a few KB means the unbundled source HTML was inlined
# instead of the bundle (the build guards against this — see git history).
curl -X POST https://webweaver-nexus-mcp.vercel.app/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"resources/read","params":{"uri":"ui://join-waitlist/mcp-app.html"},"id":1}' \
| wc -c
```
For an interactive equivalent, run MCP Inspector against the deployed URL (see [Testing with MCP Inspector](#testing-with-mcp-inspector-quick-smoke-test) above). Recommended as the first post-deploy check before bringing up basic-host.
## Publishing to the MCP registry
The registry entry is `io.github.webweaver-nexus/webweaver-mcp-server`, defined by `server.json`. Publishing is **manual dispatch only** — run the **Publish to MCP Registry** workflow from the Actions tab.
```bash
# validate locally before dispatching
mcp-publisher validate
```
**Why CI rather than publishing from your laptop.** `mcp-publisher login github` grants an orgWhat people ask about webweaver-mcp-server
What is webweaver-nexus/webweaver-mcp-server?
+
webweaver-nexus/webweaver-mcp-server is mcp servers for the Claude AI ecosystem. MCP server exposing WebWeaver Nexus services (waitlist signup with embedded MCP App UI, product overview, contact info) to external AI hosts over Streamable HTTP. It has 0 GitHub stars and its last recorded update is dated 2026-09-07.
How do I install webweaver-mcp-server?
+
You can install webweaver-mcp-server by cloning the repository (https://github.com/webweaver-nexus/webweaver-mcp-server) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is webweaver-nexus/webweaver-mcp-server safe to use?
+
Our security agent has analyzed webweaver-nexus/webweaver-mcp-server and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains webweaver-nexus/webweaver-mcp-server?
+
webweaver-nexus/webweaver-mcp-server is maintained by webweaver-nexus. The last recorded GitHub activity is dated 2026-09-07, with 0 open issues.
Are there alternatives to webweaver-mcp-server?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy webweaver-mcp-server to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/webweaver-nexus-webweaver-mcp-server)<a href="https://claudewave.com/repo/webweaver-nexus-webweaver-mcp-server"><img src="https://claudewave.com/api/badge/webweaver-nexus-webweaver-mcp-server" alt="Featured on ClaudeWave: webweaver-nexus/webweaver-mcp-server" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!