Helium MCP Server - News, Markets & AI

get_bias_from_url

Read-only

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',
  'evidence_failed' (all scored dimensions' quotes failed verification, so the scores do
  not match the article text), '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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes
`include_evidence`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 16, 2026

addedInput schema / properties / include_evidence

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

First observedApr 13, 2026

TDQS

A4.1/5.0

Behavior1/5

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

The description is otherwise rich—it documents failure modes, evidence statuses, scales, and the 404 'queued for ingestion' side effect. However, that side effect contradicts the annotation readOnlyHint=true: a read-only tool should not enqueue ingestion or modify server state. Per the rubric, this is an annotation contradiction.

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 purpose and usage guidance are front-loaded, and the text is organized with clear headers for success/failure/tips/args. It is somewhat long and duplicates return-value detail that an output schema would already cover, but each section earns its place for a complex tool.

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?

For a tool with two parameters and many failure/evidence modes, the description covers the important operational facts: found=true/false shapes, evidence status enums, score scales, 24-hour retry expectation, and the sibling alternative. Nothing essential appears 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 full responsibility for both parameters. The Args section gives a full-URL example for url and explains what include_evidence toggles (claim-level evidence and limitations) plus its default value.

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 uses a specific verb and resource: 'Get bias analysis for a specific article by its URL' and names the dimensions (political leaning, credibility, emotionality). It also distinguishes itself from the sibling get_source_bias by explicitly saying this is article-level rather than source-level.

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

Usage Guidelines5/5

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

It states the precise condition for use ('when you have a direct link to an article') and what it lets the agent avoid ('without needing to know the source name first'). The tip 'if you want source-level bias, use get_source_bias instead' gives an explicit alternative and when-not-to-use.

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.