What it does
The Patient Safety AI MCP server, published by csoai-org, provides tools to check drug interactions (check_drug_interactions), validate dosages (validate_dosage), assess patient risk (assess_patient_risk) and generate safety alerts. It uses evidence-based reference data.
Someone building or testing an AI assistant that needs medication-safety checks through an MCP-compatible client would reach for it. The documentation states that it is not a substitute for clinical judgement, so its outputs support rather than replace professional review.
To run it, add the server to an MCP client configuration, such as claude_desktop_config.json for Claude Desktop, or install the Python package with pip and start the patient-safety-ai-mcp command, which uses stdio transport. The documentation gives example requests that call the three named tools.
Limitations and requirements
Not a substitute for clinical judgement. Requires an MCP client configuration, such as Claude Desktop, or a pip installation of the Python package.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/patient-safety-ai-mcp
Patient Safety Ai MCP Server by MEOK AI Labs
v1.0.12As shown on registry.modelcontextprotocol.io when we last read it