Data Collection
constat.dev
This MCP server provides tools to query and retrieve FDA medical device regulatory data, including risk reviews, compliance histories, and evidence records.
ENDPOINT 1
https://constat.dev/api/mcp
MCP server metadata
- Name
- com.healthai/radar
- Version
- 0.5.3
Known tools 14
device_risk_lookupReview a medical-device category's public FDA signals by three-letter product code (e.g.
Inferred read-onlyfirm_compliance_historyBuild a recent, source-bounded FDA public-record timeline for a device firm: matched recalls, warning letters, and Form 483 citations where exact FEI numbers are available.
Inferred read-onlywatchlist_diffReturn machine-generated FDA public-record changes detected for monitored product codes since a caller-supplied date, plus each code's latest category snapshot and postmarket coverage.
Inferred read-onlydevice_evidence_lookupLook up the structured premarket evidence FDA accepted for a specific AI/ML-enabled device by 510(k) number (e.g.
Inferred read-onlyevidence_searchFind AI/ML device clearances by filter — product code, panel, applicant, and whether the submission reported clinical data, any sensitivity metric, or a PCCP.
Inferred read-onlypredicate_chainTrace 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).
Inferred read-onlyevidence_cohort_statsReporting-rate stats across the parsed AI/ML corpus (optionally by panel).
Inferred read-onlydevice_postmarket_lookupPost-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 matches for the applicant, plus per-device drift signals (adverse-event inflection, re-clearances of the same device line, software-recall patterns, predicate-cohort recall activity).
Potential side effectspostmarket_searchFind AI/ML devices by postmarket criteria — product code, panel, applicant, whether any drift signal exists, minimum recalls in 24 months, or a rising MAUDE trend.
Inferred read-onlycohort_postmarket_statsPostmarket 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 any drift signal, with a warning-letter match — every rate with its denominator inline, never pooled across devices.
Inferred read-onlyreimbursement_lookupTrace the clearance-to-payment pathway for an AI/ML device by FDA clearance number (K/DEN, e.g.
Potential side effectsreimbursement_statsDistribution of payment mechanisms across the AI/ML reimbursement corpus — pathway and distinct-device counts per mechanism (NTAP, Cat I, Cat III/APC, …) with the min/median/max dollar amounts for each.
Potential side effectsvehicle_risk_lookupLook up NHTSA safety history for a vehicle by make, model, and model year.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.com-healthai-radar]
url = "https://constat.dev/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"com-healthai-radar": {
"type": "http",
"url": "https://constat.dev/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: com-healthai-radar
Remote MCP URL: https://constat.dev/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"com-healthai-radar": {
"url": "https://constat.dev/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"com-healthai-radar": {
"type": "http",
"url": "https://constat.dev/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "com-healthai-radar",
"transport": "streamable-http",
"url": "https://constat.dev/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for constat.dev was fetched 2026-08-01T05:52:24.187Z and is being refreshed.
constat.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.