We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

LaunchSignal

MCP server by LaunchSignal

Browse approved product launches and submit new products for review on the LaunchSignal directory.

No sign-in (No account or key needed)Streamable HTTP

Connect to LaunchSignal

No sign-in needed. Connect with LaunchSignal’s own URL:

https://launchsignal.ai/mcp

Paste it into any client that supports remote MCP servers. Your client talks to LaunchSignal directly, not through mcp.tc.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/launchsignal

About

LaunchSignal is a free product-launch listing platform. This server lets an assistant list approved products, fetch one by slug, submit a new product for moderation, apply a listing boost, and verify a backlink badge for a Verified mark and free Priority placement.

It runs as a hosted Streamable HTTP endpoint at https://launchsignal.ai/mcp. No sign-in or API key is needed. Boosts run in demo mode without charge unless the operator enables Stripe payments, in which case a checkout URL is returned.

What you can do

  • List approved product launches, newest or boosted first
  • Filter listings by category with cursor pagination
  • Fetch an approved product by slug
  • Submit a product for moderation
  • Apply a Priority or Featured boost to a listing
  • Verify a LaunchSignal backlink on a product homepage

Tools 5

  • submit_product

    Submit a new product listing for moderation with name, URL, description, category, email and logo.

  • list_products

    List approved products, newest or boosted first, with optional limit, cursor and category.

  • get_product

    Fetch an approved product by slug; returns not_found if missing or not approved.

  • boost_product

    Apply a Priority or Featured boost to an approved listing; may return a Stripe checkout URL.

  • verify_backlink

    Check for a LaunchSignal link on the product homepage to grant a Verified mark and 7 free Priority…

Read from the live server on 18 Nov 2026.

Example prompts

  • List the newest AI products on LaunchSignal.

  • Show me the LaunchSignal listing for the product with slug elmren-voice.

  • Submit my product Acme Notes at https://acme.example to LaunchSignal as Productivity.

  • Verify the LaunchSignal backlink for my product slug acme-notes.

Set up

Every client connects to launchsignal.ai. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http launchsignal https://launchsignal.ai/mcp
  1. Start Claude Code and type /mcp. launchsignal should show as connected.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Customize → Connectors, click + Add, then Add custom connector.
  2. Name it LaunchSignal and paste this URL:
https://launchsignal.ai/mcp
  1. Click Add. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://launchsignal.ai/mcp and click Add.
  2. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
  2. Enter a name for the server.
  3. Under Connection, paste https://launchsignal.ai/mcp as the server URL, then for authentication choose No authentication.
  4. Check I understand and want to continue, then select Create as a plugin.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "launchsignal": {
      "url": "https://launchsignal.ai/mcp"
    }
  }
}

VS Code

Or from a terminal:

code --add-mcp '{"name":"launchsignal","type":"http","url":"https://launchsignal.ai/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "launchsignal": {
      "type": "http",
      "url": "https://launchsignal.ai/mcp"
    }
  }
}

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "launchsignal": {
      "serverUrl": "https://launchsignal.ai/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add launchsignal --url https://launchsignal.ai/mcp

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.launchsignal]
url = "https://launchsignal.ai/mcp"

Gemini CLI

gemini mcp add --transport http launchsignal https://launchsignal.ai/mcp

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "launchsignal": {
      "type": "http",
      "url": "https://launchsignal.ai/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://launchsignal.ai/mcp.

Embed

Show LaunchSignal in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![LaunchSignal on mcp.tc](https://mcp.tc/i/launchsignal/badge.svg)](https://mcp.tc/i/launchsignal)
HTML
<a href="https://mcp.tc/i/launchsignal"><img src="https://mcp.tc/i/launchsignal/badge.svg" alt="LaunchSignal on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/launchsignal.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/launchsignal" title="LaunchSignal on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/launchsignal.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the LaunchSignal card to your site.

Markdown
Add the mcp.tc card for LaunchSignal, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/launchsignal.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="launchsignal"><a href="https://mcp.tc/i/launchsignal">LaunchSignal on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![LaunchSignal on mcp.tc](https://mcp.tc/i/launchsignal/badge.svg)](https://mcp.tc/i/launchsignal)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:40 UTC.

Follow LaunchSignal and we’ll email you when something changes.

  1. , Automatic check

    2 tools changed.

    Details, 16 Nov 2026, 02:57 UTC

    Changed 2

    • submit_productdescription
      Before

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products. Errors: validation codes, rejected_policy, duplicate_domain (one listing per host), domain_previously_rejected (root domain was previously rejected; do not retry), rate_limited (3 pending per email per 24h). get_product returns not_found until the listing is approved. dry_run: true runs every check (validation, policy, duplicate, previously rejected, rate limit) without creating anything (no listing, no email); success returns {"ok":true,"dry_run":true,"would_accept":true}, failures return the same error a real submit would. Public, no auth.

      After

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products. Errors: validation codes, rejected_policy, duplicate_domain (one listing per host), domain_previously_rejected (root domain was previously rejected; do not retry), rate_limited (3 pending per email per 24h). get_product returns not_found until the listing is approved. dry_run: true runs every check (validation, policy, duplicate, previously rejected, rate limit) without creating anything (no listing, no email); success returns {"ok":true,"dry_run":true,"would_accept":true,"would_flag":false,"flags":[]}, failures return the same error a real submit would. Public, no auth. A real submit returns flagged: true when the listing is stored as pending but marked for closer review (burst of 3+ submissions sharing an IP, email domain or root domain within ~60s, or a known clone-template fingerprint); it is not reje…

    • verify_backlinkdescription
      Before

      After approval and after adding the LaunchSignal badge (https://launchsignal.ai/badge/{slug}.svg linked to https://launchsignal.ai/l/{slug}?utm_source=badge) or any link to launchsignal.ai on the product homepage, verify it. First success grants 7 days of free Priority placement (once) and a Verified mark; the snippet uses rel="nofollow". Same as POST /api/v1/products/:slug/verify-backlink. Max 3 checks per slug per day.

      After

      After approval and after adding the LaunchSignal badge (https://launchsignal.ai/badge/{slug}.svg linked to https://launchsignal.ai/l/{slug}) or any link to launchsignal.ai on the product homepage, verify it. First success grants 7 days of free Priority placement (once) and a Verified mark; the snippet uses rel="nofollow". Same as POST /api/v1/products/:slug/verify-backlink. Max 3 checks per slug per day. Approved listings are also checked automatically every day.

  2. , Automatic check

    1 tool changed.

    Details, 3 Nov 2026, 08:51 UTC

    Changed 1

    • submit_productdescription and input schema
      Before

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products. Errors: validation codes, rejected_policy, duplicate_domain (one listing per host), rate_limited (3 pending per email per 24h). get_product returns not_found until the listing is approved.

      After

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products. Errors: validation codes, rejected_policy, duplicate_domain (one listing per host), domain_previously_rejected (root domain was previously rejected; do not retry), rate_limited (3 pending per email per 24h). get_product returns not_found until the listing is approved. dry_run: true runs every check (validation, policy, duplicate, previously rejected, rate limit) without creating anything (no listing, no email); success returns {"ok":true,"dry_run":true,"would_accept":true}, failures return the same error a real submit would. Public, no auth.

      • New parameters: dry_run
  3. , Automatic check

    1 tool changed.

    Details, 23 Oct 2026, 01:38 UTC

    Changed 1

    • boost_productdescription
      Before

      Apply a Priority or Featured boost to an approved listing (slug + plan). Same as POST /api/v1/products/:slug/boost. Submit stays free — boost after approve. Demo / no charge when PAYMENTS_MODE=mock (default): returns charged:false and updated product. When PAYMENTS_MODE=stripe, returns a Checkout Session url (complete payment to activate).

      After

      Paid Priority or Featured placement for an approved listing (slug + plan). Same as POST /api/v1/products/:slug/boost. Paid placement is not available yet: this tool currently returns an isError result {"ok":false,"error":"payments_unavailable","message":"Paid placement is not available yet."} and changes nothing. Submit stays free. Free alternative: verify_backlink grants 7 days of Priority once. When payments launch it will return a Stripe Checkout url (complete payment to activate).

  4. , Automatic check

    2 tools changed.

    Details, 18 Oct 2026, 10:38 UTC

    Changed 2

    • get_productdescription
      Before

      Fetch an approved product by slug. Returns not_found if missing or not approved. Same as GET /api/v1/products/:slug.

      After

      Fetch an approved product by slug. Returns not_found if missing or not approved; a just-submitted (pending) listing returns not_found until a moderator approves it. Same as GET /api/v1/products/:slug.

    • submit_productdescription
      Before

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products.

      After

      Submit a new product listing for moderation (status: pending). Categories: SaaS, AI, Developer Tools, Design, Marketing, Productivity, Other. Same semantics as POST /api/v1/products. Errors: validation codes, rejected_policy, duplicate_domain (one listing per host), rate_limited (3 pending per email per 24h). get_product returns not_found until the listing is approved.

  5. , Automatic check

    Tracking started: 5 tools.

FAQ

Can I paste mcp.tc/i/launchsignal into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://launchsignal.ai/mcp, so your client talks to LaunchSignal directly. The quick link is for sharing: it opens this page, with setup steps for every client.

Does LaunchSignal need an API key or a sign-in?

No. LaunchSignal doesn’t ask for an account or key.

Is LaunchSignal a remote or a local server?

Remote. LaunchSignal hosts it at https://launchsignal.ai/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can LaunchSignal do?

It has 5 tools, including submit_product, list_products and get_product. You can list approved product launches, newest or boosted first, filter listings by category with cursor pagination and fetch an approved product by slug.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to LaunchSignal?

Yes. LaunchSignal’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read LaunchSignal’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with LaunchSignal. This page was built from LaunchSignal’s public metadata, last checked on 18 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.