MCP For Claude Marketplace
Agent Persona Consistency Scanner

Agent Persona Consistency Scanner MCP Connector for Claude

A+

A precision utility for measuring how closely an LLM adheres to a target persona.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

This MCP server provides advanced linguistic auditing tools to ensure AI agents maintain their intended character. By analyzing text through analyze_text_consistency, you can calculate a persona drift score based on pronoun ratios, formality levels, and vocabulary boundaries. Use get_persona_lexicon to retrieve specific constraints and calculate_formality_index to isolate tone deviations. It is an essential bridge for developers building consistent AI identities.

personalinguisticsllm-evaluationconsistencytext-analysis

3 tools expose this connector's capabilities to your AI agent.

analyze_text_consistency

Performs a comprehensive linguistic audit of a text segment to determine how well it fits a specific persona profile

calculate_formality_index

Isolates the formality component to determine if the text's tone is too casual or too formal for the persona

get_persona_lexicon

Retrieves the specific list of forbidden words and required linguistic markers for a given persona

See how to talk to your AI agent using Agent Persona Consistency Scanner.

Analyze this text for persona consistency: 'I am a professional assistant. I will help you with your tasks.' using persona ID 'prof_01'.

{ "pronounRatio": 1.0, "formalityScore": 0.0, "violationCount": 0, "driftScore": 0.0 }

What are the forbidden words for the 'Victorian Gentleman' persona?

The forbidden words for the Victorian Gentleman persona include: 'algorithm', 'internet', 'smartphone', and 'digital'.

Check the formality of this text: 'Hey, what's up? I'm just chilling.'

{ "contractionDensity": 2.0 }

The drift score is an aggregate metric derived from deviations in pronoun usage, contraction density (formality), and the presence of forbidden words found via `analyze_text_consistency`.

Related Connectors

Claim Substantiation Checker

Claim Substantiation Checker MCP

4 tools Official

Scans marketing copy for factual and numeric claims requiring substantiation.

A+ View details →
LinkedIn Scannability & Reading Time Scorer

LinkedIn Scannability & Reading Time Scorer MCP

4 tools Official

Calculate exact scannability metrics for LinkedIn feeds, including reading time and mobile viewport impact.

A+ View details →
Sensitive Data Exposure Detector

Sensitive Data Exposure Detector MCP

3 tools Official

Intercepts and redacts sensitive information from file reads and tool outputs.

A+ View details →
Dialogue Tree Complexity Analyzer

Dialogue Tree Complexity Analyzer MCP

3 tools Official

Analyze structural complexity, branching, and localization costs of dialogue trees.

A+ View details →