This server provides MCP tools to access and render hourly Briefing Service publications: list available briefings, fetch structured briefings, quick summaries, provenance/candidate data, e-ink page images, and custom rendering.
list_briefings – List all 11 briefing keys, names, and prices.
get_briefing(key) – Get a full structured briefing: lead story, ranked stories, research, why-it-matters, key points.
get_summary(key) – Get free headlines and one-line summaries for a briefing.
get_candidates(key) – Get free provenance dump of every candidate story, outlets, selection status, and duplicate collapses.
get_page(key, page, wide) – Get a rendered 480x800 1-bit PNG page (or 800x480 wide front page) for e-ink displays.
render_briefing(feeds, persona) – Rank and render a custom briefing from your own feeds and persona (requires Reader key with render credits or x402).
Served locally over stdio or remotely via streamable HTTP, with free tier, Reader key, and x402 payment options.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
MCP server for Briefing Service: every hour an LLM editor ranks ~100 feeds per topic (AI news, AI research, frontier labs, markets, US sports, European football, US news, world, crypto & onchain) plus two daily editions (Grants & Funding: newly posted federal funding notices with Deadline / Amount / Eligible on every item; Noticias Lentas: the day's news in simple Spanish at CEFR B1 with a glossary) and publishes the result as structured JSON, a rendered 480x800 e-ink page, a multi-page Morning Paper PDF, and a free provenance dump of every candidate it saw.
This package runs locally over stdio and calls the public REST API. The same tools are served remotely (streamable HTTP, no install) at https://briefing-service.wholemind.workers.dev/mcp.
Claude Desktop / Claude Code / Cursor / any stdio client:
{
"mcpServers": {
"briefings": {
"command": "npx",
"args": ["-y", "briefing-mcp"],
"env": { "BRIEFING_KEY": "" }
}
}
}Claude Code one-liner:
claude mcp add briefings -- npx -y briefing-mcpClaude Desktop, one click: download briefing-mcp-0.1.0.mcpb and open it (MCP bundle; it asks for the optional Reader key).
Related MCP server: storyflo
tool | what it returns | cost |
| the 11 keys ( | free |
| lead, ranked stories, research, why-it-matters, key points | 25 free/IP/day, then key or x402 |
| headlines and one-liners | free |
| every candidate this hour: canonical link, outlets, | free |
| 480x800 1-bit PNG (or 800x480 wide front page) | 25 free/IP/day |
Free: 25 JSON/page/tool calls per IP per day, plus the summary and candidates endpoints.
Reader key: $9/month, unlimited reads and Morning Paper delivery. Set it as BRIEFING_KEY. Buy at https://briefing-service.wholemind.workers.dev/billing/checkout
Per call: x402 (USDC on Base) against the remote endpoint.
Docs for agents: https://briefing-service.wholemind.workers.dev/llms.txt
index.js is the whole server: it registers five tools with @modelcontextprotocol/sdk and answers each by calling the public Briefing Service REST API over HTTPS (GET /v1/briefings/...). It stores nothing, runs no shell commands, and reads only two environment variables (BRIEFING_KEY, BRIEFING_BASE_URL). The Dockerfile builds the same thing; docker run -i speaks MCP over stdio.
Run the smoke test locally:
npm install
node client-test.mjs # lists tools and calls list_briefings, get_summary, get_candidates, get_page, get_briefingWrite-up of the pipeline (collect, entity-overlap dedupe, LLM editor, 1-bit render) and what the first week taught: https://dev.to/jshelley/i-built-an-hourly-newspaper-for-e-ink-and-turned-the-pipeline-into-an-mcp-server-1ebg. Each briefing also has an Atom feed at /v1/briefings/{key}/feed.xml; the Morning Paper PDF carries an outline per story, front-page go-to links and a clickable source URL on every story page.
BRIEFING_KEY: optional Reader key (sent as Authorization: Bearer).
BRIEFING_BASE_URL: override the API base (default: the public service).
MIT
One briefing as structured JSON: lead story, ranked stories and research items with summaries, why-it-matters and key points, plus when it was ranked.
Inputs: key (required).
Free provenance dump: every candidate the editor saw this hour with canonical_link, published time, feed weight, the other outlets that ran the story (also_in), a selected flag, and collapsed duplicates (duplicate_of, dup_rule, dup_score).
Inputs: key (required).
One rendered page of a briefing as a 480x800 1-bit PNG (page 0 is the front page; story pages follow). Made for e-ink and small displays. wide=true returns the 800x480 landscape front page.
Inputs: key (required), page, wide.
Free, small: headlines and one-line summaries of a briefing (for widgets and quick reads).
Inputs: key (required).
List the hourly briefings available (key and name), with prices.
Inputs: no named parameters.
Rank and render a briefing from your own feeds and persona (one editor run; needs a Reader key with render credits, or use x402 on the remote endpoint). Returns JSON and page URLs.
Inputs: feeds (required), persona (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool targets a distinct facet: listing, full JSON, lightweight summary, provenance candidates, image pages, and rendering. The only mild overlap is get_summary vs get_briefing, but the descriptions make the size/format tradeoff clear enough to choose correctly.
All six tools follow a strict verb_noun snake_case pattern (list_briefings, get_briefing, get_summary, get_candidates, get_page, render_briefing). No style mixing or vague standalone verbs.
Six tools is well-scoped for a briefing service, with one clear tool per access mode (list, full read, quick summary, provenance, visual page, render). Nothing feels padded or missing from the count.
The surface covers discovery, full and lightweight retrieval, provenance, paginated rendering, and custom rendering. Minor gaps exist (no date-range search or explicit pagination for list_briefings, and only passive retrieval of pages), but core workflows are covered.
Free cross-lingual news briefings for AI agents across 89 languages. Read-only, hosted.
Managed cloud RSS and Atom feed reader with a remote Model Context Protocol (MCP) endpoint. Zero server setup required — enables AI agents like Claude to instantly subscribe to feeds, search full-text articles, extract readable content, and access curated AI editions ("Your Newspaper") over secure streamable HTTP.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
