"TED" matching MCP servers:

Enables staged, auditable medical literature reviews—search, screening, fetch, and wiki—that produce an evidence-linked Obsidian wiki, with screening decisions, extracted mentions, and synthesis citations checked against stored source text.

Automatically analyzes and dispatches user tasks to appropriate handlers, supporting development task processing via Miyabi Agent and medical AI academic article generation. Provides intelligent task classification and routing for development, writing, and general tasks.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

Analyzes clinical trial site feasibility, enrollment velocity, eligibility criteria, and benchmark performance across ClinicalTrials.gov's registry via a structured MCP interface.

Enables AI agents to access FDA and ClinicalTrials.gov data for medical device compliance, adverse event monitoring, and regulatory due diligence.

Enables Type 1 diabetes patients and caregivers to monitor real-time blood glucose from Dexcom Share, calculate insulin doses, and receive empathetic AI-powered sick day care guidance through natural language interactions.