Constat MCP — FDA Device Evidence Lifecycle is an MCP server with 14 tools an agent can call, among them cohort_postmarket_stats, device_evidence_lookup, device_postmarket_lookup. It answers at https://constat.dev/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
FDA & NHTSA regulatory risk for agents: compliance, 510(k) evidence, postmarket, reimbursement.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 any drift signal, with a warning-letter match — every rate with its denominator Inputs: panel |
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 — validation study design, sample sizes, endpoints, reported performance, predicate ch Inputs: k_number |
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 matches for the applicant, plus per-device drift signals (adverse-event inflection, r Inputs: k_number |
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, warning-letter matches, a normalized category signal, its driver contributions, and i Inputs: product_code |
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 devices' — never a pooled performance value. Excludes not-yet-parsed devices from e Inputs: panel |
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. Answers 'what evidence did FDA accept for devices like mine'. Returns bounded dis Inputs: product_code, panel, applicant, has_clinical_data, reports_any_sensitivity_metric, has_pccp |
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 are available. Product codes are discovered from Constat's AI/ML-device corpus or Inputs: firm_name, product_codes, fei_numbers, since, limit |
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 trend. Returns per-device postmarket summaries with drift-signal counts. Inputs: product_code, panel, applicant, has_drift_signal, signal_specificity, min_recalls_24mo |
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/ML devices chain to older predicates. Inputs: k_number, depth |
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 mechanism (NTAP add-on, Category I/III CPT + CMS rate, HCPCS, MAC LCD) with amou Inputs: k_number, cpt_code |
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 rate'. Filters: mechanism, CPT category, NTAP status, applicant. Returns pathways Inputs: mechanism, cpt_category, ntap_status, applicant, has_cms_rate, limit |
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 the min/median/max dollar amounts for each. Deliberately never a single pooled 'r |
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 components). Inputs: make, model, year |
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 and postmarket coverage. Defaults to Constat Radar's five-code watchlist and the Inputs: product_codes, since, limit |
Every block below points at https://constat.dev/api/mcp. Pick your client and copy.
claude mcp add --transport http constat-mcp-fda-device-evidence https://constat.dev/api/mcp
{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://constat.dev/api/mcp"]
}
}
}{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"url": "https://constat.dev/api/mcp"
}
}
}{
"servers": {
"constat-mcp-fda-device-evidence": {
"type": "http",
"url": "https://constat.dev/api/mcp"
}
}
}{
"context_servers": {
"constat-mcp-fda-device-evidence": {
"url": "https://constat.dev/api/mcp"
}
}
}{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"serverUrl": "https://constat.dev/api/mcp"
}
}
}{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"url": "https://constat.dev/api/mcp"
}
}
}name: Constat MCP — FDA Device Evidence Lifecycle
version: 0.0.1
schema: v1
mcpServers:
- name: Constat MCP — FDA Device Evidence Lifecycle
type: streamable-http
url: https://constat.dev/api/mcp{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"httpUrl": "https://constat.dev/api/mcp"
}
}
}{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"type": "http",
"url": "https://constat.dev/api/mcp"
}
}
}{
"mcpServers": {
"constat-mcp-fda-device-evidence": {
"url": "https://constat.dev/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fconstat.dev%2Fapi%2Fmcp&type=streamable_http&id=constat-mcp-fda-device-evidence&name=Constat%20MCP%20%E2%80%94%20FDA%20Device%20Evidence%20Lifecycle
It answered our last check on 18 October 2026 in 606 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
14, as returned by the server's own tools/list on 31 August 2026: cohort_postmarket_stats, device_evidence_lookup, device_postmarket_lookup, device_risk_lookup, evidence_cohort_stats, evidence_search, firm_compliance_history, postmarket_search, and 6 more.
It answered our last check on 18 October 2026 in 606 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://constat.dev/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.healthai. Endpoint host: constat.dev. ARD identifier: urn:air:com.healthai:mcp:radar.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.