
Shipstry MCP server
Which MCP servers are Shipstry's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-19
- Registry namecom.shipstry/launch-dataverified in the MCP registry
The registry name sits under shipstry.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools7
- Server calls itselfshipstry-launch-data
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 43 ms.
- Its tools do none of the product's use cases we checked: submit a product to a weekly launch registry; collect upvotes during an assigned ship week; have a product hand-submitted to many backlink directories.
Once connected
- Parameters are untyped or undescribed in 5 of 7 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score70 of 100answers 100 · does the job 0 · definitions 88 · context 100 · connects 100
- What an agent can do with it0 of 3 use cases
- Answered100% of days8 of 8 daily checks
- Median first answer471 ms
- Space in an agent's context≈ 1,442 tokensthe definitions of all its tools (7), which an agent carries on every turn
- Tool definitionsB · 88 of 100
- Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 5 of 7
What an agent can do with it
- cannot · submit a product to a weekly launch registry
- cannot · collect upvotes during an assigned ship week
- cannot · have a product hand-submitted to many backlink directories
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_categoriesList Shipstry's product categories with the number of approved products in each. Call this first when you need a valid category slug for the other tools.
search_launchesSearch approved Shipstry launches by keyword, category, or tag. Keyword matching covers product name and tagline. Returns compact records with votes, ship week, awards, and the canonical Shipstry URL.
get_launchFetch one approved launch with its description, tags, awards, and maker name. Identify it by Shipstry product id, product slug, its Shipstry URL, or its own website URL.
list_ship_weekList the products that launched in one ship week (Monday-Sunday UTC, keyed YYYYMMDD). Defaults to the current week. During Fog Mode vote counts for the current week are hidden and the order is random.
get_winnersWeekly or monthly medal winners (gold, silver, bronze). Returns the most recent periods by default, or one period when `period` is given. Use this to see what actually won, not just what launched.
get_category_landscapeBenchmark a category over a window of ship weeks: how many products launched, the vote distribution (mean, p50, p75, p90, max), the top launches, how many medals were awarded, and the tags that appear most. Use this to judge how crowded a…
check_urlCheck whether a website URL is already listed on Shipstry, using the same normalization as submission duplicate detection. Only approved listings are visible.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"launch-data": {
"type": "http",
"url": "https://shipstry.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http shipstry https://shipstry.com/mcpclaude.ai, ChatGPT and other clients: add https://shipstry.com/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.