Helium MCP Server - News, Markets & AI

get_source_bias

Read-only

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').
            Compact names ('NBC News' -> 'NBC') resolve too. Ambiguous input returns candidate sources.
    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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`source`	Yes
`include_html`	No
`recent_articles`	No
`include_evidence`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedJul 16, 2026

addedInput schema / properties / include_evidence

Added value: +{
+  "default": false,
+  "title": "Include Evidence",
+  "type": "boolean"
+}

addedInput schema / properties / include_html

Added value: +{
+  "default": false,
+  "title": "Include Html",
+  "type": "boolean"
+}

First observedApr 13, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare readOnlyHint=true and destructiveHint=false, and the description does not contradict them. It adds substantial behavioral detail: deterministic match method, error on missing source, candidate-source returns on ambiguity, optional include_evidence payload tradeoffs, legacy score labeling, and methodology caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with a one-line purpose, a detailed return-field list, and a separate Args section. The length is justified by the tool's complex, multi-field response, and the most decision-relevant information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's four parameters, rich response structure, and existing output schema, the description is very complete. It covers return fields, parameter semantics, error behavior, ambiguity handling, and performance-related payload caveats, leaving no critical invocation detail missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the entire semantic burden for parameters. The Args section fully explains source identifier formats, resolution and ambiguity behavior, recent_articles range and default, plus the meaning and purpose of include_evidence and include_html.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Get comprehensive bias analysis for a news source.' It further clarifies the accepted identifier types (name, slug, or domain), which distinguishes it from sibling tools like get_bias_from_url and get_all_source_biases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use case is implied by the tool name and description, but there is no explicit guidance about when to choose this tool over alternatives such as get_bias_from_url or get_all_source_biases. The source identifier semantics and error behavior are useful context, but they do not provide when/when-not selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Helium MCP Server - News, Markets & AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.