get_bias_from_url

io.github.connerlambden/helium-mcp · Verify this server

Get bias analysis for a specific article by its URL. Use this when you have a direct link to an article and want to know its political leaning, credibility, emotionality, and other bias dimensions — without needing to know the source name first. On success (found=true), returns: - article_id, classification_id, requested_url, matched_url, title, source, date, link, category - teaser: article excerpt - summary: one-sentence AI summary - context: AI-generated context for the article - implicit_assumptions: tacit or unstated premises the article's claims or framing rely on (list of concise strings, when available) - extracted_data: structured quantitative/qualitative facts extracted from the article - raw_data: legacy serialized form of extracted_data - bias_description: narrative description of this specific article's bias - bias_values: dict of per-dimension article scores using canonical plain-text keys, e.g. {"liberal conservative bias": 4, "overall credibility": 7, "emotional bias": -5, ...} Article scores use -10 to +10 for bipolar dimensions and 0 to 10 for unipolar dimensions. Positive values lean toward the second pole of each dimension (conservative, authoritarian, etc.). - bias_analysis_status: 'evidence_ready', 'evidence_unverified', 'evidence_partial', 'scored_legacy', or 'pending' - bias_dimensions when include_evidence=true: each dimension's score, scale, evidence status, claim, verbatim evidence, counterevidence, confidence, and rationale. Quotes include verification method and exact character offsets when raw-text matching succeeds. Dimension evidence_status is one of: verified, provided_unchecked, quote_mismatch, metadata_incomplete, metadata_only, or missing. - bias_analysis: contract/schema/model/prompt provenance, generation and review status, input scope/hash/size, analysis target, quote-verification method, explicit missingness and evidence coverage, and case-specific limitations - total_shares: total social shares - wayback_link: Wayback Machine archive URL if available - image: article image URL if available On failure (found=false, HTTP 404): - found: false - message: explanation string The URL is automatically queued for ingestion; retry after ~24 hours. Tip: if you want source-level bias (not article-level), use get_source_bias instead. Tip: bias_values keys here use plain-text format (e.g. 'liberal conservative bias') shared with the other bias tools where that dimension is available. Args: url: Full article URL, e.g. 'https://www.nytimes.com/2024/01/01/us/politics/example.html'. include_evidence: Include claim-level evidence and limitations. Defaults to true.