Patient Safety AI MCP
This MCP server provides clinical safety decision-support tools for medication and patient risk analysis.
Check drug-drug interactions from comma-separated medication lists.
Assess patient risk using age, conditions, medications, BMI, and smoker status.
Validate medication dosage against safe ranges using dose, frequency, age, and weight.
Generate formatted clinical safety alerts for interactions, allergies, dosage, or contraindications.
Check allergy conflicts and cross-reactivity for a medication against listed allergies.
All tools are read-only, stateless/idempotent, with free-tier rate limits and optional API key support.
mcp-name: io.github.CSOAI-ORG/patient-safety-ai-mcp
Patient Safety Ai MCP
Check drug interactions, validate dosages, assess patient risk, and generate safety alerts
Check drug interactions, validate dosages, assess patient risk, and generate safety alerts. Uses evidence-based reference data. Not a substitute for clinical judgement.
š Quick Start
# Install via pip
pip install patient_safety_ai_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install patient-safety-ai-mcp --client claudeRelated MCP server: Risk Assessment AI MCP
⨠Features
Real-time AI safety monitoring
Byzantine fault-tolerant consensus
EU AI Act compliance tracking
Incident alert system
Multi-agent governance
š Documentation
š”ļø Compliance
This MCP server is built with EU AI Act compliance built-in:
ā Article 9 ā Risk Management System
ā Article 13 ā Transparency & Instructions for Use
ā Article 15 ā Bias Detection & Testing
ā Article 26 ā FRIA Support (where applicable)
ā Article 50 ā AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic ā
How MEOK charges
MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.
This repository's source is MIT-licensed and free to self-host.
š¤ Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem ā 300+ MCP servers for sovereign AI governance.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
š License
MIT Ā© CSOAI-ORG
Pairs with MEOK Governance Suite
Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool ā EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.
# One-shot install of the governance pack
npx meok-setup --pack governanceā Full catalogue: councilof.ai ā MEOK AI Labs: meok.ai
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"patient-safety-ai-mcp": {
"command": "uvx",
"args": ["patient-safety-ai-mcp"]
}
}
}Or: pip install patient-safety-ai-mcp then run the patient-safety-ai-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
"Use
check_drug_interactionsto ā¦""Use
assess_patient_riskto ā¦""Use
validate_dosageto ā¦"
Available Tools
5 toolsassess_patient_riskA
Risk scoring based on patient conditions, age, and comorbidities. Conditions and medications as comma-separated strings.
Behavior: This tool is read-only and stateless ā 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 structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: age (int): The age to analyze or process. conditions (str): The conditions to analyze or process. medications (str): The medications to analyze or process. bmi (float): The bmi to analyze or process. smoker (bool): The smoker to analyze or process. api_key (str): The api key to analyze or process.
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 ā 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.
Inputs: age (required), conditions (required), medications (required), bmi, +2 more. Returns: result
check_allergy_conflictsA
Cross-reference a medication against patient allergies including cross-reactivity. Allergies as comma-separated string.
Behavior: This tool is read-only and stateless ā 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 structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: medication (str): The medication to analyze or process. allergies (str): The allergies to analyze or process. api_key (str): The api key to analyze or process.
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 ā 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.
Inputs: allergies (required), medication (required), api_key. Returns: result
check_drug_interactionsA
Check known drug interaction databases for a list of medications. Pass drugs as comma-separated string.
Behavior: This tool is read-only and stateless ā 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 structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: drugs (str): The drugs to analyze or process. api_key (str): The api key to analyze or process.
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 ā 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.
Inputs: drugs (required), api_key. Returns: result
generate_safety_alertA
Create a formatted clinical safety alert. Alert types: interaction, allergy, dosage, contraindication.
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 structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: drug (str): The drug to analyze or process. alert_type (str): The alert type to analyze or process. severity (str): The severity to analyze or process. patient_id (str): The patient id to analyze or process. details (str): The details to analyze or process. api_key (str): The api key to analyze or process.
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 ā 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.
Inputs: drug (required), alert_type (required), api_key, details, +2 more. Returns: result
validate_dosageA
Check dosage against known safe ranges for a medication.
Behavior: This tool is read-only and stateless ā 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 structured analysis or classification of inputs against established frameworks or standards.
When NOT to use: Not suitable for real-time production decision-making without human review of results.
Args: drug (str): The drug to analyze or process. dose_mg (float): The dose mg to analyze or process. frequency_per_day (int): The frequency per day to analyze or process. patient_age (int): The patient age to analyze or process. patient_weight_kg (float): The patient weight kg to analyze or process. api_key (str): The api key to analyze or process.
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 ā 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.
Inputs: drug (required), dose_mg (required), api_key, patient_age, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 5 tools
Each tool targets a distinct aspect of patient safety: risk assessment, allergy conflicts, drug interactions, dosage validation, and alert generation. There is no functional overlap, and descriptions clearly differentiate their purposes.
All tool names use snake_case and follow a verb_noun pattern. Two tools start with 'check', while the others use different verbs (assess, generate, validate), which is mostly consistent but not perfectly uniform.
With 5 tools, the server covers essential patient safety checks without being bloated or too sparse. Each tool serves a clear purpose within the domain.
The toolset covers core safety checks (risk, allergies, interactions, dosage) and includes alert generation. Minor gaps exist, such as no dedicated contraindication check, but overall it addresses the main clinical safety concerns.
Maintenance
Related MCP Connectors
AI governance MCP server for EU AI Act compliance and jurisdiction verification
MEOK MCP Hardening MCP ā automated security red-team for any MCP server. Maps OWASP LLM Top 10
Agent Orchestrator MCP Server by MEOK AI Labs
MCP server for the Fail Modes taxonomy ā a knowledge base of AI system failure modes
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceClinical Trials AI - MCP server providing AI-powered tools and automation by MEOK AI Labs4 npm41 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceRisk Assessment AI - MCP server providing AI-powered tools and automation by MEOK AI Labs4 npm37 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceHealth Check AI - MCP server providing AI-powered tools and automation by MEOK AI Labs3 npm42 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceHIPAA Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs28 PyPIMIT