Consent-gated tools that turn user health notes into non-diagnostic appointment-prep materials.
Scored across 5 tools
The four authoring tools each target a distinct input type (chronology, sensation vocabulary, appointment goals, flare phases), so boundaries are mostly clear from the descriptions. The only potentially confusing pair is prepare_appointment_brief vs render_appointment_brief, but the descriptions distinguish structuring from rendering well enough to avoid misselection.
All names use snake_case with a leading verb (build_, find_, prepare_, reflect_, render_), which is a predictable, readable pattern. The lone deviation is the verb_preposition form reflect_on_flare, but it does not break comprehension.
Five tools is well-scoped for a focused health-observation structuring service, and each tool occupies a distinct role in the workflow. Nothing appears redundant or padded.
The set covers the main lifecycle: distilling inputs (timeline, symptom words, flare, goals) and producing/rendering an appointment brief. Coverage is solid, though there is no tool for revising or merging an existing structured artifact beyond the prepare-then-render path.
Sorts non-identifying, user-authored observations into a factual chronology while preserving supplied dates and uncertainty. Requires explicit consent for transient processing. PHI and diagnosis are outside its scope.
Inputs: observations (required), consentConfirmed (required). Returns: timeline, disclaimer, changePoints
Organises a non-identifying, user-authored sensation description into neutral sensation, timing, pattern and impact vocabulary. Requires explicit consent for transient processing. PHI and diagnostic inference are outside its scope.
Inputs: description (required), consentConfirmed (required), impact, timing, +1 more. Returns: prompts, disclaimer, starterSentence, originalDescription
Structures non-identifying goals, changes, impacts, user-stated medicines and questions into an appointment brief. Requires explicit consent for transient processing. PHI, diagnosis and treatment advice are outside its scope.
Inputs: mainGoal (required), consentConfirmed (required), changes, impacts, +3 more. Returns: changes, impacts, mainGoal, medicines, +3 more
Structures non-identifying before, during and recovery observations, presenting suspected patterns as questions rather than causes. Requires explicit consent for transient processing. PHI is outside its scope.
Inputs: consentConfirmed (required), during, recoveryAfter, baselineBefore, +1 more. Returns: during, disclaimer, recoveryAfter, baselineBefore, +1 more
Renders a supplied, complete, non-identifying appointment brief as an accessible card. Requires explicit consent for transient processing. Preserves the supplied fields and disclaimer; PHI is outside its scope.
Inputs: changes (required), impacts (required), mainGoal (required), medicines (required), +4 more. Returns: changes, impacts, mainGoal, medicines, +3 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Your labs, wearables, DNA and notes as one health record your AI agent can read (OAuth 2.1).
Free health tools: explain lab results and prescriptions, when to seek care, clinics nearby.
Your MedNode health vault in your AI assistant — records, summaries, labs, appointments.
Verified identity plus consented personal context, starting with medical records, images & insurance
Add one secure layer between your agents and this server.
