# BedrockNews MCP server

GRIN-scored news for agents: discover by verdict, pull full analysis, traverse extraction graphs.

## Links
- Registry page: https://www.getdrio.com/mcp/com-bedrocknews-news
- Website: https://bedrocknews.com

## Install
- Endpoint: https://api.bedrocknews.com/api/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://api.bedrocknews.com/api/mcp

## Tools
- list_stories - Discover BedrockNews stories with GRIN-aware filters. Filter by verdict ('extractive' | 'mixed' | 'generative'), plumb range (0-100 analytical-clarity score), editorialMode ('grin' news/politics | 'culture' | 'research' | 'ledger'), category (see list_categories), date window (since/before, ISO 8601), or a title search (substring match on titles, not full text). Sorted newest first; paginated via cursor. Returns compact story briefs — use get_article for full analysis. Endpoint: https://api.bedrocknews.com/api/mcp
- get_article - Fetch one BedrockNews story by id. Returns the transformed article plus its full structured analysis (GRIN scores, extraction graph, key stats, trajectory, what-to-watch). Pass fields:'grin' to get just the analysis payload without the heavy body text. Story ids contain slashes (e.g. 'ledger/2026/apr/06/iran-war-math-doesnt-work') — pass them verbatim. Endpoint: https://api.bedrocknews.com/api/mcp
- get_extraction_graph - Return a story's extraction map as a real graph — nodes + edges data, not a picture. This is the load-bearing artifact for agents: re-render it in any style, or analyze who extracts value from whom. 'Not found' can mean the story has no graph (culture/research modes, or older transforms). Endpoint: https://api.bedrocknews.com/api/mcp
- get_related - Related BedrockNews stories for a given article — same section, ranked by editorial-mode match, plumb, source affinity, and recency. Endpoint: https://api.bedrocknews.com/api/mcp
- list_categories - The BedrockNews category taxonomy: ids (valid values for list_stories' category filter), display names, and which editorial framework each category runs (grin | culture | auto). Endpoint: https://api.bedrocknews.com/api/mcp
- get_site_info - BedrockNews metadata: what the site is, how the GRIN/CLAIMS/NOVEL frameworks work, terms of use + attribution, and every machine-readable surface. Also returns the full capability map (every tool, prompt, and resource) — call this first. Endpoint: https://api.bedrocknews.com/api/mcp

## Resources
- bedrocknews://front-page - The current BedrockNews front page as structured JSON — story briefs with plumb, GRIN scores, and verdicts. One read instead of polling list_stories. MIME type: application/json
- https://bedrocknews.com/llms.txt - Curated site map + editorial-framework overview for LLMs. MIME type: text/markdown
- https://bedrocknews.com/llms-full.txt - The full API-for-agents reference: endpoints, filters, schema, terms. MIME type: text/markdown
- https://bedrocknews.com/schema/v1/article.json - The versioned JSON Schema for the public article contract. MIME type: application/schema+json

## Prompts
- daily_plumb - Brief on today's highest-plumb stories — the pieces with the clearest analysis — optionally scoped to one category. Arguments: category
- extractive_or_generative - Sourced verdict on whether current coverage of a topic is extractive or generative, using GRIN scores — no vibes, cite stories. Arguments: topic
- map_extraction - Pull a story's extraction graph (real nodes+edges) and re-render it: narrate who extracts value from whom. Arguments: story
- research_radar - Triage recent research stories through the CLAIMS framework: what's claimed, how solid, what would change the picture. Arguments: topic

## Metadata
- Owner: com.bedrocknews
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 30, 2026
- Source: https://registry.modelcontextprotocol.io