Constat MCP — FDA Device Evidence Lifecycle
com.healthai/radarhealthai.comstreamable-httpv0.5.3Scanned
FDA and CMS evidence for AI medical devices: 510(k), postmarket, reimbursement, and compliance.
14 tools: 14 change things.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 8 findings
Tools listed without sign-in. Remote posture
With Anlyon
14 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Constat MCP — FDA Device Evidence Lifecycle can do
The Constat MCP — FDA Device Evidence Lifecycle is published by healthai.com, a domain the MCP Registry verified. It has 14 tools. It can create or change data (14 tools: device_risk_lookup, firm_compliance_history, watchlist_diff, device_evidence_lookup and 10 more), but cannot delete data. None of its tools only reads.
1 tool brings in text other people can write (device_risk_lookup).
The fixed checks matched 8 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 0.5.3.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Changes things 14Claude Code: ask
cohort_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, wi…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 inline, never pooled across devices.
Annotations the server declares
- title: Summarize Postmarket Cohort
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
device_evidence_lookupLook up the structured premarket evidence FDA accepted for a specific AI/ML-enabled device by 510(k) number (e.g.1 finding
Why it is in this group
- The name "device_evidence_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "device_evidence_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "device_evidence_lookup" says "lookup": a word for reading.
Description, as the server wrote it 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 chain, PCCP — each with a verbatim source quote and page. Null means the summary did not state it.
Annotations the server declares
- title: Look Up Device Evidence
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
device_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…No findings
Why it is in this group
- The name "device_postmarket_lookup" says "lookup": a word for reading.
- The description's first verb is "post": a word for a change.
Description, as the server wrote it 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, re-clearances of the same device line, software-recall patterns, predicate-cohort recall activity). Descriptive observables with sources — never a safety judgment.
Annotations the server declares
- title: Look Up Device Postmarket Signals
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
device_risk_lookupReview a medical-device category's public FDA signals by three-letter product code (e.g.Reads text others write1 finding
Why it is in this group
- The name "device_risk_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Findings
- Warn
The server marks "device_risk_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "device_risk_lookup" says "lookup": a word for reading.
Description, as the server wrote it 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 interpretation limits. It does not predict enforcement against a firm.
Annotations the server declares
- title: Review Device Category Risk Signals
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
evidence_cohort_statsReporting-rate stats across the parsed AI/ML corpus (optionally by panel).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 every denominator and discloses the parse queue separately. Predicate age (median years between a clearance and its cited predicates) is included when decision-date coverage clears a 60% floor, and withheld otherwise.
Annotations the server declares
- title: Summarize Evidence Cohort
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
evidence_searchFind AI/ML device clearances by filter — product code, panel, applicant, and whether the submission reported clinical data, any sensitivity metric, or a PCCP.1 finding
Why it is in this group
- The name "evidence_search" says "search": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "evidence_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "evidence_search" says "search": a word for reading.
Description, as the server wrote it 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 discovery summaries; call device_evidence_lookup with a result's K-number for the full source-quoted FDA record. Presence flags are descriptive: 'reports a sensitivity metric' is not 'reports a comparable sensitivity' — analysis units differ across devices.
Annotations the server declares
- title: Search Device Evidence
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
firm_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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 may be supplied explicitly. Returns attribution and coverage limits with the records; it is not a finding of noncompliance or a prediction of FDA action.
Annotations the server declares
- title: Review Firm Compliance History
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
postmarket_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.1 finding
Why it is in this group
- The name "postmarket_search" says "search": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "postmarket_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "postmarket_search" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search Postmarket Signals
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
predicate_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).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Trace Predicate Chain
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
reimbursement_lookupTrace the clearance-to-payment pathway for an AI/ML device by FDA clearance number (K/DEN, e.g.1 finding
Why it is in this group
- The name "reimbursement_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "reimbursement_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "reimbursement_lookup" says "lookup": a word for reading.
Description, as the server wrote it 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 amounts, effective dates, and source links, plus any commercial/MAC payer coverage policies that reference the clearance or its codes. Answers 'who got paid, how much, through which mechanism, on what basis.' CPT codes are bare factual identifiers only — no procedure descriptors; follow the CMS source link for the official descriptor.
Annotations the server declares
- title: Look Up Reimbursement Pathways
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
reimbursement_searchFind AI/ML device payment pathways by mechanism — e.g.1 finding
Why it is in this group
- The name "reimbursement_search" says "search": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "reimbursement_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "reimbursement_search" says "search": a word for reading.
Description, as the server wrote it 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 with amounts, effective dates, and sources. Use reimbursement_stats for the mechanism distribution (never a single pooled reimbursement rate).
Annotations the server declares
- title: Search Reimbursement Pathways
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
reimbursement_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 do…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 'reimbursement rate': NTAP add-on amounts and CMS rates are different measurements and are reported separately with their own spreads.
Annotations the server declares
- title: Summarize Reimbursement Cohort
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
vehicle_risk_lookupLook up NHTSA safety history for a vehicle by make, model, and model year.1 finding
Why it is in this group
- The name "vehicle_risk_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "vehicle_risk_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "vehicle_risk_lookup" says "lookup": a word for reading.
Description, as the server wrote it 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).
Annotations the server declares
- title: Look Up Vehicle Safety History
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
watchlist_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 cover…1 finding
Why it is in this group
- The name "watchlist_diff" says "diff": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "watchlist_diff" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "watchlist_diff" says "diff": a word for reading.
Description, as the server wrote it 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 last seven days. Analyst verdict text and internal review status are excluded; use next_since as the next polling cursor.
Annotations the server declares
- title: Poll Watchlist Changes
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:40 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 14
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 14 tools that change things (14 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://constat.dev/api/mcp: tools/list returned 14 tools to an anonymous client, including device_risk_lookup (write), firm_compliance_history (write), watchlist_diff (write), device_evidence_lookup (write), evidence_search (write) and 9 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "device_risk_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "device_risk_lookup" says "lookup": a word for reading.
- Warnwatchlist_diff
The server marks "watchlist_diff" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "watchlist_diff" says "diff": a word for reading.
The server marks "device_evidence_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "device_evidence_lookup" says "lookup": a word for reading.
- Warnevidence_search
The server marks "evidence_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "evidence_search" says "search": a word for reading.
The server marks "postmarket_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "postmarket_search" says "search": a word for reading.
The server marks "reimbursement_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "reimbursement_lookup" says "lookup": a word for reading.
Show 2 more findingsShow fewer
The server marks "reimbursement_search" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "reimbursement_search" says "search": a word for reading.
The server marks "vehicle_risk_lookup" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"openWorldHint":false}; The name "vehicle_risk_lookup" says "lookup": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:device_risk_lookupChanges thingsinputSchema
Install
Pinned to version 0.5.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http radar https://constat.dev/api/mcpclaude mcp add --transport http radar https://constat.dev/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__radar__device_risk_lookup",
"mcp__radar__firm_compliance_history",
"mcp__radar__watchlist_diff",
"mcp__radar__device_evidence_lookup",
"mcp__radar__evidence_search",
"mcp__radar__predicate_chain",
"mcp__radar__evidence_cohort_stats",
"mcp__radar__device_postmarket_lookup",
"mcp__radar__postmarket_search",
"mcp__radar__cohort_postmarket_stats",
"mcp__radar__reimbursement_lookup",
"mcp__radar__reimbursement_search",
"mcp__radar__reimbursement_stats",
"mcp__radar__vehicle_risk_lookup"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as radar. Review it before you use it.
Capability tags behind 1 rule
- mcp__radar__device_risk_lookup untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.healthai/radar/verify?hash=1b12cc2603c3c7c43a62f61d77228735152a61120b9ca1d017aab9383aa9e2e1" | jq -e '.changed == false'Pinned hash 1b12cc2603c3, from Nov 10, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.healthai/radar/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.healthai/radar)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:56 UTC.
Constat MCP — FDA Device Evidence Lifecycle: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Constat MCP — FDA Device Evidence Lifecycle safe?
- No scan can promise that. What its definitions show: 14 tools, 14 of which can change, send or delete something, and 8 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Constat MCP — FDA Device Evidence Lifecycle delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Constat MCP — FDA Device Evidence Lifecycle do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Constat MCP — FDA Device Evidence Lifecycle have?
- 14 tools: 14 write. device_risk_lookup, firm_compliance_history, watchlist_diff, device_evidence_lookup, evidence_search, predicate_chain, evidence_cohort_stats, device_postmarket_lookup and 6 more.
Does the Constat MCP — FDA Device Evidence Lifecycle need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Constat MCP — FDA Device Evidence Lifecycle send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Constat MCP — FDA Device Evidence Lifecycle changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.