get_source_bias

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

Get comprehensive bias analysis for a news source. Returns: - source_name, slug_name, page_url - source_match: original query and deterministic match method - articles_analyzed: total articles in the bias database for this source - last_updated: source-profile aggregation timestamp - avg_social_shares: average social shares per article - emotionality_score (0-10): how emotional the writing is - prescriptiveness_score (0-10): how much the source tells readers what to think/do - bias_values: canonical plain-text source-level weighted display scores (-50 to +50 bipolar, 0 to +50 unipolar). Keys match the article tools; these are directional source summaries, not raw article-score averages. - bias_scores: legacy emoji-prefixed display scores - bias_score_methodology: scope and evidence caveats for aggregate scores - bias_description: clean-text, AI-generated overall bias summary narrative - bias_description_metadata: generation time, automated review status, and evidence scope - bias_description_html: optional website HTML when include_html=true - liberal_conservative_description: narrative on political leaning - libertarian_authoritarian_description: narrative on authority stance - signature_phrases: words/phrases uniquely overrepresented vs other sources - signature_negative_phrases: uniquely negative/alarming phrases - most_shared_phrases: phrases in their most viral articles - most_emotional_phrases: phrases used in their most emotional articles - pays_for_traffic_keywords: keywords this source buys ads for - similar_sources: sources with the most similar bias profile - most_different_sources: sources with the most different bias profile - trends_graph_url: URL to a chart of this source's coverage volume over time - bias_plot_urls: dict of 2D bias scatter plot image URLs (political_lib_auth, subjective_objective, informative_opinion, oversimplification_factful) — only present when available - recent_articles: list of most recent articles with full article fields, bias_values, analysis status, and optional self-contained bias_dimensions and bias_analysis. Evidence quotes include verification method and exact character offsets when available. - recent_evidence_coverage: reconciled counts for verified, unverified, partial, legacy-scored, and pending articles, plus evidence-bearing count and verified ratio Throws an error if the source is not found. Args: source: Source name, slug, or domain (e.g. 'Fox', 'reuters', 'bbc.co.uk'). Partial names are accepted only when they identify one source; ambiguous input returns candidates. recent_articles: Number of recent articles to include (1-50, default 10). include_evidence: Include per-article claims, verbatim evidence, counterevidence, confidence, rationale, and limitations. Defaults to false to keep multi-article source payloads compact. include_html: Also return the original website-formatted source narrative. Defaults to false.