Rehabilitation Monitoring MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REHAB_DATA_DIR | No | Override the default data directory. Default is ./data | ./data |
| FIRECRAWL_API_KEY | Yes | API key for Firecrawl to enable research search tool | |
| FIRECRAWL_API_URL | No | Optional custom Firecrawl API endpoint |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_patient_informationC | Get patient information from the available rehabilitation data sources. |
| calculate_patient_risk_scoresB | Calculate rehabilitation risk scores using patient records, therapy sessions, wearable measurements, and medication adherence data. |
| identify_declining_rehabilitation_outcomesC | Identify patients whose rehabilitation outcomes are declining across the available measurements. |
| generate_rehabilitation_reportsA | Generate a markdown rehabilitation report for one patient or the whole cohort. |
| create_patient_alertsB | Create and persist alerts for patients whose rehabilitation risk or declines cross the configured thresholds. |
| search_rehabilitation_researchC | Search Firecrawl for rehabilitation-related research papers and summaries. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| generate_patient_progress_summaries | Generate a patient progress summary using CSV-backed rehabilitation data. |
| create_rehabilitation_monitoring_reports | Create a rehabilitation monitoring report from the available data. |
| explain_risk_classifications | Explain how the rehabilitation risk classifications are determined. |
| recommend_follow_up_actions | Recommend follow-up actions based on the monitoring data. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| patients.csv | Patient records stored in patients.csv |
| therapy_sessions.csv | Therapy session data stored in therapy_sessions.csv |
| wearable_measurements.csv | Wearable sensor measurements stored in wearable_measurements.csv |
| medication_adherence.csv | Medication adherence records stored in medication_adherence.csv |
| alerts.json | Persisted rehabilitation alerts created by the server |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: risk calculation, alert creation, report generation, patient info retrieval, outcome decline detection, and research search. No overlap in functionality.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., calculate_patient_risk_scores, create_patient_alerts, generate_rehabilitation_reports). No deviations.
Six tools is well-scoped for a rehabilitation monitoring server, covering the core tasks without being too few or excessive.
The tools cover risk assessment, alerting, reporting, patient info, outcome decline identification, and research. Minor gaps exist (e.g., no tool for inputting or updating patient measurements), but the surface is largely complete for monitoring and analysis.