Scoopkit

dev.scoopkitPublished by scoopkit.devOfficial publisherv1.0.1Updated Oct 29, 2026

AI-industry news for agents: each story once, as a sourced event in a 10/57 taxonomy. No key needed.

VerifiedStreamable HTTPWeb executableWeb Search & Scraping Knowledge & Memory

Server details

Identifier: dev.scoopkit/mcp
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified that this server's namespace belongs to scoopkit.dev, which also runs its endpoint. That identifies the publisher; it does not make the server's tools safe.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/dev.scoopkit%2Fmcp.svg)](https://sourceweft.com/mcp/dev.scoopkit%2Fmcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Scoopkit is a hosted MCP server that gives assistants deduplicated, sourced AI-industry news events classified in a 10/57 taxonomy.

What you can do: List and filter events by category, subcategory and date range, with cursor pagination
Fetch a single event by ID, including its sources and correction history
Browse the public category and subcategory taxonomy
Run semantic, natural-language search over events (Pro tier)
Request a free API key by email through a magic link
When to use it: Useful when an assistant needs current AI-industry news — model releases, funding rounds, story updates — as clean structured events rather than scattered articles, for example answering questions about what shipped this week or how a story changed.
Requirements: Remote Streamable HTTP endpoint; nothing to install or run. Works without a key on the free tier (last 45 days, 100 calls a day). An optional X-Api-Key header ties usage to an account; a free key comes from the signup page or the request_magic_link tool, and a Pro key adds semantic search, a 12-month archive and 10,000 calls a day.

Before you install

The X-Api-Key header is a credential; keep it out of shared configs. request_magic_link sends an email to the address supplied, so confirm the address with the user first. All other tools are read-only. Free tier omits paid-only fields and excludes some paid-primary content, and search returns 403 without a Pro key.

Installation

In SourceWeft

Open Scoopkit in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.scoopkit%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "scoopkit": {
      "type": "http",
      "url": "https://api.scoopkit.dev/mcp"
    }
  }
}

README

[Scoopkit]

Scoopkit MCP server

[MCP Registry] [Endpoint] [Free tier] [Glama]

AI-industry news for agents. When a model ships, forty outlets write about it; Scoopkit returns the story once, as a structured event classified against a published taxonomy (10 categories, 57 subcategories), with its sources and a correction_history showing how the story changed.

This repo holds setup docs and an Agent Plugins manifest (plugin.json, mcp.json), no server code. The server is hosted at https://api.scoopkit.dev/mcp (Streamable HTTP). There is nothing to install or run.

No API key needed to start. Without a key you get the free tier: the last 45 days of events, 100 calls a day. A free key (same limits, tied to you) comes from scoopkit.dev/start or the request_magic_link tool. A Pro key adds semantic search, a 12-month archive and 10,000 calls a day.

Try it without an MCP client: api.scoopkit.dev/v1/demo/events returns the latest events as JSON, no key, so you can see the shape before connecting anything.

Tools

Tool	What it does	Key
`list_events`	Newest events first. Filter by `category`, `subcategory`, `since`, `until`; paginate with `cursor`, `limit` (max 100)	optional
`get_event`	One event by `event_id`, with its sources and correction history	optional
`taxonomy`	The category and subcategory tree, e.g. `MODEL_RELEASE`, `FUNDING_AND_DEALS`	none
`search`	Semantic search over events (`q`, `limit`)	Pro
`request_magic_link`	Emails the user a sign-in link that issues a free key (`email`)	none

All tools except request_magic_link are read-only.

Setup

Claude (claude.ai and desktop)

Settings → Connectors → Add custom connector → URL https://api.scoopkit.dev/mcp.

Claude Code

bash

claude mcp add --transport http scoopkit https://api.scoopkit.dev/mcp# with a key:claude mcp add --transport http scoopkit https://api.scoopkit.dev/mcp --header "X-Api-Key: YOUR_KEY"

claude mcp add --transport http scoopkit https://api.scoopkit.dev/mcp# with a key:claude mcp add --transport http scoopkit https://api.scoopkit.dev/mcp --header "X-Api-Key: YOUR_KEY"

Cursor

~/.cursor/mcp.json:

VS Code

.vscode/mcp.json:

json

{  "servers": {    "scoopkit": {      "type": "http",      "url": "https://api.scoopkit.dev/mcp"    }  }}

{  "servers": {    "scoopkit": {      "type": "http",      "url": "https://api.scoopkit.dev/mcp"    }  }}

Cline

cline_mcp_settings.json:

json

{  "mcpServers": {    "scoopkit": {      "type": "streamableHttp",      "url": "https://api.scoopkit.dev/mcp"    }  }}

{  "mcpServers": {    "scoopkit": {      "type": "streamableHttp",      "url": "https://api.scoopkit.dev/mcp"    }  }}

With a key, add "headers": { "X-Api-Key": "YOUR_KEY" } next to url in any of the JSON configs above.

Things to ask

"What AI models were released this week?"
"Show me AI funding rounds since October 1st, with sources."
"What changed in the story about event evt_…?"

Tools

request_magic_link

Email a Scoopkit API key sign-in link

Request 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 enumeration). **For agents helping a human get set up:** this endpoint is the only step you can call directly. The next step — opening the emailed link and clicking "Reveal my key" on `GET /v1/auth/verify` — **requires a real human click and cannot be automated or done on the human's behalf.** This is intentional: it's what stops email security scanners (e.g. Microsoft Safe Links) from silently consuming the link before the person ever sees it. Tell the human: check your email, open the link, click the button, then paste the key back here. **Not a pollable async job.** This 202 has no `Location`/`job_id` to poll — the next step is a human clicking an emailed link, not a machine checking a status endpoint. ### Responses: **202**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json { "accepted": true, "detail": "Detail" } ```

Parametersemailrequired

list_events

List AI news events

List 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 fields by omission (never null) and excludes paid-primary subcategories entirely; archive depth is 45 days on free, 365 on Pro. Over MCP the X-Api-Key header is optional: without it you get the free tier, limited to 100 calls a day per caller. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json { "data": [ { "event_id": "Event Id", "schema_version": "Schema Version", "taxonomy_version": "Taxonomy Version", "primary_category": "Primary Category", "subcategory": "Subcategory", "categories": [ "string" ], "type_confidence": 1.0, "headline": "Headline", "summary": "Summary", "reported_at": "2023-01-01T00:00:00Z", "orgs": [ "string" ], "models": [ "string" ], "source_url": "Source Url", "article_count": 1 } ], "pagination": { "has_more": true, "count": 1 }, "meta": { "request_id": "Request Id", "taxonomy_version": "Taxonomy Version", "tier": "ApiTier" } } ```

Parameterslimitsinceuntilcursorcategorysubcategory

get_event

Get an AI news event

Get 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. Over MCP the X-Api-Key header is optional (free tier without it). ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json { "data": { "event_id": "Event Id", "schema_version": "Schema Version", "taxonomy_version": "Taxonomy Version", "primary_category": "Primary Category", "subcategory": "Subcategory", "categories": [ "string" ], "type_confidence": 1.0, "headline": "Headline", "summary": "Summary", "reported_at": "2023-01-01T00:00:00Z", "orgs": [ "string" ], "models": [ "string" ], "source_url": "Source Url", "article_count": 1 }, "meta": { "request_id": "Request Id", "taxonomy_version": "Taxonomy Version", "tier": "ApiTier" } } ```

Parametersevent_idrequired

search

Search AI news events

Semantic 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 or above; free-tier keys get 403 with an upgrade_url. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json { "data": [ { "event_id": "Event Id", "schema_version": "Schema Version", "taxonomy_version": "Taxonomy Version", "primary_category": "Primary Category", "subcategory": "Subcategory", "categories": [ "string" ], "type_confidence": 1.0, "headline": "Headline", "summary": "Summary", "reported_at": "2023-01-01T00:00:00Z", "orgs": [ "string" ], "models": [ "string" ], "source_url": "Source Url", "article_count": 1, "relevance_score": 1.0 } ], "pagination": { "has_more": true, "count": 1 }, "meta": { "request_id": "Request Id", "taxonomy_version": "Taxonomy Version", "tier": "ApiTier" } } ```

Parametersqrequiredlimit

taxonomy

Get the event taxonomy

Get Taxonomy Public taxonomy — no API key required. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json

Takes no parameters.

Version history

v1.0.1LatestOct 29, 2026
v1.0.0Sep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts