Robin Saige we check the tools AI agents call

Constat MCP — FDA Device Evidence Lifecycle

com.healthai/radar

FDA and CMS evidence for AI medical devices: 510(k), postmarket, reimbursement, and compliance.

— the operator's own registry description reported

Publisher com.healthai · first seen 2026-08-12 · endpoint https://constat.dev/api/mcp

allow
verdict
mid-slow-solo
cluster
ok_tools
answers
14
tools served

Dependency rating derived

allow — mid-slow-solo — safe to depend on

Cluster mid-slow-solo · distinctiveness 0.304 (typical). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency521 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools14
vs populationmid
capabilities1
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_3e11f5174296621f4bee8c8d · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

cohort_postmarket_stats device_evidence_lookup device_postmarket_lookup device_risk_lookup evidence_cohort_stats evidence_search firm_compliance_history postmarket_search predicate_chain reimbursement_lookup reimbursement_search reimbursement_stats vehicle_risk_lookup watchlist_diff

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.

legibility checktools passingok
name is clear & specific14/14
has a description14/14
description is substantive14/14
parameters are typed14/14
parameters are described11/1411/14

14 of 14 tools graded · 14 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2025-06-18
protocol version
session model
0.5.3
server version com.healthai/radar

Capabilities: tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:58:12Zok_tools2005212025-06-18
2026-08-12T05:33:26Zok_tools2003352025-06-18

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/com.healthai/radar.svg)](https://robinsaige.com/s/com.healthai/radar)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview