io.github.CSOAI-ORG/bias-detection-mcp

Describe an AI system in one sentence -> instant bias risk assessment. No API key required. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Analyze text for demographic bias patterns, stereotyping, and unfair language. Args: model_output: The AI-generated text to analyze for bias. protected_attributes: Comma-separated list of attributes to check (e.g. "race,gender,age"). Leave empty for auto-detection. api_key: Optional MEOK API key for pro tier. Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Calculate fairness metrics from prediction data. Input format: comma-separated values with group labels. Provide predictions as 'group:prediction' pairs separated by commas. Example: "male:1,female:0,male:1,female:1,male:0,female:0" If ground_truth is provided, use same format for actual outcomes to compute equalized odds and calibration metrics. Args: predictions: Comma-separated group:prediction pairs (e.g. "male:1,female:0,male:1"). ground_truth: Optional comma-separated group:actual pairs for outcome-based metrics. api_key: Optional MEOK API key for pro tier. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Get detailed remediation steps for a specific type of AI bias. Args: bias_type: Type of bias to get recommendations for. Options: selection, measurement, confirmation, automation, aggregation, representation, evaluation, historical. api_key: Optional MEOK API key for pro tier. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Check bias requirements against EU AI Act Article 10 and NIST AI RMF MAP requirements. Args: jurisdiction: Jurisdiction to check against. Options: eu, us_nist, uk, all. api_key: Optional MEOK API key for pro tier. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation. When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice. Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent — calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Compute demographic parity ratios across protected groups (EU AI Act Article 10). Args: predictions: Comma-separated `group:prediction` pairs (prediction is 0 or 1). Example: "male:1,female:0,male:1,female:1,male:0,female:0" protected_attribute: Optional label of the protected attribute (gender, age, race…). Pure documentation — used in the response narrative. api_key: Optional MEOK API key (free tier gets a sanitised summary). Returns: Dict with: - selection_rate_per_group: P(Y=1 | group=g) for each group - demographic_parity_ratio: min(rate)/max(rate) — 1.0 = perfect parity - passes_four_fifths_rule: ratio ≥ 0.80 (EEOC 4/5ths rule, cited by EU AI Act Recital 72) - largest_gap: absolute difference between most- and least-selected groups - severity_band: critical/concerning/borderline/good/excellent - article_10_interpretation: how this evidence maps to AI Act Article 10(2)(f), 10(3), 10(4) - remediation_actions: concrete next steps (data rebalancing, post-processing, etc.) Behavior: Read-only, stateless, idempotent. Free tier: 10/day. PAYG: £0.05/call. Pro: unlimited. Example: analyze_demographic_parity( predictions="male:1,male:1,male:1,male:0,female:1,female:0,female:0,female:0", protected_attribute="gender" ) # → demographic_parity_ratio=0.33 (1/4 vs 3/4) → fails 4/5ths, "critical"