# Healthai Radar MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.healthai%2Fradar
Registry id: `mcp-registry/com.healthai/radar`
Status: live (checked 2026-10-27T02:48:01.791Z)

## Verdict

Healthai Radar MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1198 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (95/100) across 14 tools, costing an agent about 3,404 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1198 ms | 14% of MCP servers |
| p95 handshake latency | 3142 ms | — |
| Checks in 30 days | 4,927 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 14 | — |
| Tool-list size for an agent | ~3,404 tokens | 44% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "healthai-radar-mcp-server": {
      "type": "http",
      "url": "https://constat.dev/api/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http healthai-radar-mcp-server https://constat.dev/api/mcp
```

## Tools (14)

- `cohort_postmarket_stats`: Postmarket presence rates across the snapshotted AI/ML device cohort (optionally by panel): share with any recall in 24 months, with a rising MAUDE trend, with 
- `device_evidence_lookup`: Look up the structured premarket evidence FDA accepted for a specific AI/ML-enabled device by 510(k) number (e.g. K252148). Returns parsed summary fields — vali
- `device_postmarket_lookup`: Post-clearance intelligence for one AI/ML device by 510(k) number: its product code's recalls, MAUDE adverse-event level and trend, warning-letter and 483 match
- `device_risk_lookup`: Review a medical-device category's public FDA signals by three-letter product code (e.g. FRN = infusion pump). Returns recalls, MAUDE adverse-event trend, warni
- `evidence_cohort_stats`: Reporting-rate stats across the parsed AI/ML corpus (optionally by panel). Each rate is a presence figure with its denominator — 'reported in X of Y audited dev
- `evidence_search`: Find AI/ML device clearances by filter — product code, panel, applicant, and whether the submission reported clinical data, any sensitivity metric, or a PCCP. A
- `firm_compliance_history`: Build a recent, source-bounded FDA public-record timeline for a device firm: matched recalls, warning letters, and Form 483 citations where exact FEI numbers ar
- `postmarket_search`: Find AI/ML devices by postmarket criteria — product code, panel, applicant, whether any drift signal exists, minimum recalls in 24 months, or a rising MAUDE tre
- `predicate_chain`: Trace the predicate ancestry of a 510(k) device, with each cited predicate's age (how many years old the predicate was when the child cleared). Reveals how AI/M
- `reimbursement_lookup`: Trace the clearance-to-payment pathway for an AI/ML device by FDA clearance number (K/DEN, e.g. DEN170073) OR bare CPT code (e.g. 75580). Returns every payment 
- `reimbursement_search`: Find AI/ML device payment pathways by mechanism — e.g. 'devices that got NTAP', 'devices paid under a Category I CPT code', 'pathways with a known CMS dollar ra
- `reimbursement_stats`: Distribution of payment mechanisms across the AI/ML reimbursement corpus — pathway and distinct-device counts per mechanism (NTAP, Cat I, Cat III/APC, …) with t
- `vehicle_risk_lookup`: Look up NHTSA safety history for a vehicle by make, model, and model year. Returns recall campaigns and complaint statistics (crashes, fires, injuries, top comp
- `watchlist_diff`: Return machine-generated FDA public-record changes detected for monitored product codes since a caller-supplied date, plus each code's latest category snapshot 

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.