hcp-engagement
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_API_KEY | No | API key to protect the HTTP endpoint. Always set for public deployments. | |
| SUPABASE_URL | Yes | The URL of your Supabase project. Reuse the same value as the Frescopa .env. | |
| SUPABASE_ANON_KEY | Yes | The anon (read-only) key for your Supabase project. Reuse the same value as the Frescopa .env. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| hcp_list_hcpsA | List Healthcare Professionals (HCPs). Filter by specialty, tier (A|B|C), region, or state. Mock data — not real providers. |
| hcp_searchA | Search HCPs by name, NPI, or institution (partial match). |
| hcp_get_profileA | Full profile for one HCP by NPI: demographics, consent status per channel, and engagement summary. |
| hcp_list_interactionsA | List rep-HCP interactions (visits, calls, emails). Filter by HCP NPI, region, specialty, rep name, interaction type, or how many days back. |
| hcp_engagement_summaryA | Analytics: total interactions, recency, sentiment score, and samples per HCP. Sorted by most interactions first. Useful for finding engagement gaps (e.g. Tier A HCPs with no recent contact). |
| hcp_prescribing_trendsA | Monthly prescribing trend (new Rx, total Rx, market share %) for an HCP, optionally scoped to one product. Requires npi. |
| hcp_prescribing_trend_by_segmentA | Quarterly prescribing trend for one product, broken out by region and specialty (segment_rollup), plus per-HCP quarterly rows (hcp_quarterly) for drill-down into which specific HCPs are declining/growing. Use segment_rollup to compare regions/specialties side by side; use hcp_quarterly to find individual decliners within a flagged segment. |
| hcp_visit_frequency_by_segmentB | Quarterly rep interaction/visit frequency broken out by region and specialty — meant to be compared side by side with hcp_prescribing_trend_by_segment's segment_rollup for the same quarters. |
| hcp_rep_activityB | Per-rep territory summary: HCPs engaged, total interactions, interactions in last 30 days, average sentiment. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target distinct resources or views: search/list/get HCPs, raw interactions, rep summaries, engagement analytics, and prescribing trends. The overlaps between hcp_list_hcps and hcp_search, and between the segment rollup tools, are manageable because descriptions specify different filters and metrics.
All tools share a consistent hcp_ prefix and descriptive names. However, the set mixes verb-led names like hcp_list_hcps and hcp_get_profile with noun-phrase names like hcp_rep_activity and hcp_engagement_summary, so the pattern is not perfectly uniform.
Nine tools is well-scoped for an HCP engagement analytics domain. Each tool covers a meaningful capability, from individual HCP lookup and interaction history to rep-level activity and segment-level prescribing trends, without unnecessary redundancy.
The tool set covers the core read-only engagement workflow: finding HCPs, viewing profiles, inspecting interactions, and aggregating engagement and prescribing trends at both individual and segment levels. Minor gaps exist, such as no dedicated rep directory or HCP/consent update capability, but agents can work around these with existing tools.