
Scoopkit MCP server
Which MCP servers are Scoopkit'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 2026-10-26
- Registry namedev.scoopkit/mcpverified in the MCP registry
The registry name sits under scoopkit.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools5
- Server calls itselfScoopkit API
- Server versionScoopkit MCP server — v0.1.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 120 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 3 of 5 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 score86 of 100answers 100 · definitions 90 · context 100 · use 12 · connects 100
- Use2 GitHub stars
- Answered100% of days9 of 9 daily checks
- Median first answer150 ms
- Space in an agent's context≈ 1,782 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 90 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 5
What an agent can do with it
- not sure · collapse duplicate AI headlines into one event
- not sure · classify AI industry stories by primary category
- not sure · feed AI agents structured news events via MCP
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 →
request_magic_linkRequest a free API key by email Step 1 of self-serve signup — no key required. Sends a one-time link to `email`; always returns 202 with the same accepted:true body whether or not that address already has a key (prevents account…
list_eventsList events, newest first The primary resource — one structured event per underlying story, already deduplicated from many source articles. Cursor-paginated (`next_cursor`/`has_more`), newest `reported_at` first. Free tier omits paid-only…
get_eventGet a single event by ID 404s if the event doesn't exist, is unpublished, is beyond your tier's archive window, or was soft-deleted — never distinguishes which, to avoid leaking data existence beyond what the tier allows. ### Responses…
searchSemantic search over events (Pro+) Natural-language query embedded and ranked by cosine similarity against published events — not a keyword/text match. Each result is a normal event object plus `relevance_score` (0-1). Requires Pro tier…
taxonomyGet Taxonomy Public taxonomy — no API key required. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"scoopkit": {
"type": "http",
"url": "https://api.scoopkit.dev/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http scoopkit https://api.scoopkit.dev/mcpclaude.ai, ChatGPT and other clients: add https://api.scoopkit.dev/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.
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.