Journalistic Reasoning Prover MCP Connector for Claude
A+A report cited three sources. None of them existed. That is not an error � that is fabrication. Journalistic Reasoning Prover forces independent verification, source tracing, and false balance detection grounded in the SPJ Code of Ethics.
AI agents produce content that mimics journalism but fails under basic verification. They cite 'experts' without naming them. They invent studies. NewsGuard (2024) found that 73% of AI-generated articles contained at least one unverifiable claim. That's not a source — that's a hallucination.
The Problem It Solves
AI-generated reporting fails for five specific reasons:
- Source fabrication — Citing sources that don't exist. 'According to reports' is an evasion, not a citation.
- Claim unverified — Presenting assertions as facts. 'It is well established' replaces independent corroboration.
- False balance — Giving equal weight to evidence-based and fringe positions. Presenting 97% consensus alongside 3% dissent as 'both sides' is distortion.
- Attribution stripped — Using quotes or statistics without naming who produced them, when, where, and how. 'Crime is up 40%' is assertion, not journalism.
- Conflict concealed — Failing to disclose financial, institutional, or personal conflicts of interest.
Key Benefits
- Forces source verification — Every factual claim must trace to a named, verifiable primary source.
- Demands claim corroboration — Requires independent verification from at least two sources per Kovach & Rosenstiel standards.
- Detects false balance — Weights perspectives proportional to evidence, not equally.
- Requires complete attribution — Mandates who, when, where, and how for every quote and statistic.
- Enforces conflict disclosure — Checks for financial, institutional, and personal conflicts before publication.
Framework Coverage
- SPJ Code of Ethics — Seek truth, minimize harm, act independently
- Kovach & Rosenstiel (2014) — The verification discipline
- Craig Silverman Handbook — Systematic verification methodology
- IFCN Principles — International fact-checking standards
- Vosoughi et al. (2018) — MIT research on false news spread
- NewsGuard (2024) — AI misinformation data
Related Connectors
Clinical Reasoning Prover MCP
Forces AI to validate clinical treatment plans against US guidelines (AHA, ACC) using real differential exclusion, explicit pharmacokinetics, and objective triage scales instead of subjective descriptors and diagnostic anchoring.
First Principles Prover MCP
LLMs reason by analogy, copying industry norms. This engine is a 6-pivot cognitive trap that forces the agent to discard jargon and derive original solutions exclusively from physical, mathematical, or logical axioms.
Feynman Radical Simplification Prover MCP
Stop your AI from hiding behind jargon — force it to explain simply, build from scratch, and justify every piece of complexity.
Data Pipeline Prover MCP
A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pipeline ran for 3 months — silently inserting 2.4 million duplicate records and serving stale data to dashboards nobody questioned. This tool forces schema validation at boundaries, idempotent writes, freshness alerting, and end-to-end lineage tracing.