Fda risk radar MCP agent

Constat — FDA & NHTSA regulatory-risk MCP server for AI agents.

by thehealthai·MIT license·★ 0 Stars on the repo·GitHub ↗

Files of Fda risk radar MCP

thehealthai/main1 file
README.md
Show the full text102 lines
fda-risk-radar-mcp/README.md102 lines · 5.3 KB

Constat — 483 Risk Radar (MCP server)

Constat MCP — FDA Device Evidence Lifecycle MCP connector – tool definition quality and endpoint health on Glama

Constat 483 Risk Radar MCP server

MCP Queen grade

The MCP server behind Constat — FDA & NHTSA regulatory-risk intelligence for AI agents, over the Model Context Protocol. Live public regulatory data — recalls, adverse events, warning letters, 510(k) premarket evidence, postmarket drift signals, reimbursement pathways, and vehicle safety. Decision support, not regulatory advice.

  • Endpoint: https://constat.dev/api/mcp (legacy https://radar.healthai.com/api/mcp still serves)
  • Transport: Streamable HTTP (JSON-RPC 2.0)
  • Auth: none for anonymous access (10 work units/min and 50/day per anonymous source); an optional X-API-Key header enables the separately assigned metered allowance. Tool calls have documented work-unit costs.
  • Registry: com.healthai/radar (official MCP registry)

The evidence corpus and tool logic run hosted at the endpoint above. This repo also ships server.mjs, a zero-dependency stdio bridge to that endpoint, so stdio-only MCP clients can use the server like any local one:

node server.mjs            # stdio MCP server, bridges to constat.dev/api/mcp
// e.g. in an MCP client config
{ "mcpServers": { "constat": { "command": "node", "args": ["/path/to/server.mjs"] } } }
docker build -t constat-mcp . && docker run -i constat-mcp   # same, containerized

Tools

Tool What it does
device_risk_lookup FDA compliance risk for a device category by 3-letter product code — recalls, MAUDE trend, warning-letter matches, composite score
firm_compliance_history Source-bounded FDA public-record timeline for a device firm — recalls, warning letters, 483s, clearances
watchlist_diff Machine-detected FDA public-record changes for monitored product codes since a given date
device_evidence_lookup Parsed 510(k) premarket evidence for an AI/ML device, each field with a verbatim source quote + page
evidence_search Find AI/ML clearances by product code, panel, applicant, clinical data, sensitivity metric, or PCCP
predicate_chain Trace a device's predicate ancestry with each predicate's age at clearance
evidence_cohort_stats Reporting-rate stats across the parsed AI/ML corpus — presence figures with denominators
device_postmarket_lookup Post-clearance intelligence for one device — recalls, MAUDE trend, letter/483 matches, drift signals
postmarket_search Find devices by postmarket criteria — drift signals, recalls in 24mo, rising MAUDE trend
cohort_postmarket_stats Postmarket presence rates across the AI/ML cohort, each with its denominator
reimbursement_lookup Clearance-to-payment pathway by K/DEN or CPT code — NTAP, Cat I/III, CMS rates, HCPCS, LCDs
reimbursement_search Find payment pathways by mechanism, CPT category, NTAP status, applicant
reimbursement_stats Mechanism distribution across the reimbursement corpus with dollar ranges
vehicle_risk_lookup NHTSA safety history by make/model/year — recall campaigns and complaint stats

Quick start

curl -s https://constat.dev/api/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"device_risk_lookup","arguments":{"product_code":"FRN"}}}'

List tools with {"method":"tools/list"}. Note the Accept header must include text/event-stream (streamable-HTTP requirement).

Each of the 14 tools declares an output schema. Tool calls return structured content with an explicit ok, not_found, invalid_request, or unavailable status while preserving a text result for older clients.

The tools are observational and non-destructive, but advertise readOnlyHint: false because calls write bounded quota and operational- telemetry state. They do not publish or modify FDA, CMS, NHTSA, or other third-party records.

See the integration guide, architecture and trust boundaries, privacy notice, and support page.

  • Clarity MCP — condition-aware ingredient, product & supplement safety (verdict + evidence tier + citation).
  • MCP Queen — the graded MCP registry that independently probes and grades this server.

About

Built by Health AI, the team behind Constat. Informational only; verify against primary FDA/NHTSA sources.

License

MIT — see LICENSE.

1# Constat — 483 Risk Radar (MCP server)
2 
3[![Constat MCP — FDA Device Evidence Lifecycle MCP connector – tool definition quality and endpoint health on Glama](https://glama.ai/mcp/connectors/com.healthai/radar/badges/score.svg)](https://glama.ai/mcp/connectors/com.healthai/radar)
4 
5<a href="https://glama.ai/mcp/servers/@thehealthai/fda-risk-radar-mcp">
6 <img width="380" height="200" src="https://glama.ai/mcp/servers/@thehealthai/fda-risk-radar-mcp/badge" alt="Constat 483 Risk Radar MCP server" />
7</a>
8 
9[![MCP Queen grade](https://mcpqueen.com/badge/com.healthai/radar.svg)](https://mcpqueen.com/s/com.healthai/radar)
10 
11The MCP server behind [**Constat**](https://constat.dev) — FDA & NHTSA
12regulatory-risk intelligence for AI agents, over the Model Context Protocol.
13Live public regulatory data — recalls, adverse events, warning letters, 510(k)
14premarket evidence, postmarket drift signals, reimbursement pathways, and
15vehicle safety. **Decision support, not regulatory advice.**
16 
17- **Endpoint:** `https://constat.dev/api/mcp` (legacy `https://radar.healthai.com/api/mcp` still serves)
18- **Transport:** Streamable HTTP (JSON-RPC 2.0)
19- **Auth:** none for anonymous access (10 work units/min and 50/day per
20 anonymous source); an optional `X-API-Key` header enables the separately
21 assigned metered allowance. Tool calls have documented work-unit costs.
22- **Registry:** [`com.healthai/radar`](https://registry.modelcontextprotocol.io) (official MCP registry)
23 
24The evidence corpus and tool logic run hosted at the endpoint above. This repo
25also ships `server.mjs`, a zero-dependency **stdio bridge** to that endpoint, so
26stdio-only MCP clients can use the server like any local one:
27 
28```bash
29node server.mjs # stdio MCP server, bridges to constat.dev/api/mcp
30```
31 
32```jsonc
33// e.g. in an MCP client config
34{ "mcpServers": { "constat": { "command": "node", "args": ["/path/to/server.mjs"] } } }
35```
36 
37```bash
38docker build -t constat-mcp . && docker run -i constat-mcp # same, containerized
39```
40 
41## Tools
42 
43| Tool | What it does |
44|------|--------------|
45| `device_risk_lookup` | FDA compliance risk for a device category by 3-letter product code — recalls, MAUDE trend, warning-letter matches, composite score |
46| `firm_compliance_history` | Source-bounded FDA public-record timeline for a device firm — recalls, warning letters, 483s, clearances |
47| `watchlist_diff` | Machine-detected FDA public-record changes for monitored product codes since a given date |
48| `device_evidence_lookup` | Parsed 510(k) premarket evidence for an AI/ML device, each field with a verbatim source quote + page |
49| `evidence_search` | Find AI/ML clearances by product code, panel, applicant, clinical data, sensitivity metric, or PCCP |
50| `predicate_chain` | Trace a device's predicate ancestry with each predicate's age at clearance |
51| `evidence_cohort_stats` | Reporting-rate stats across the parsed AI/ML corpus — presence figures with denominators |
52| `device_postmarket_lookup` | Post-clearance intelligence for one device — recalls, MAUDE trend, letter/483 matches, drift signals |
53| `postmarket_search` | Find devices by postmarket criteria — drift signals, recalls in 24mo, rising MAUDE trend |
54| `cohort_postmarket_stats` | Postmarket presence rates across the AI/ML cohort, each with its denominator |
55| `reimbursement_lookup` | Clearance-to-payment pathway by K/DEN or CPT code — NTAP, Cat I/III, CMS rates, HCPCS, LCDs |
56| `reimbursement_search` | Find payment pathways by mechanism, CPT category, NTAP status, applicant |
57| `reimbursement_stats` | Mechanism distribution across the reimbursement corpus with dollar ranges |
58| `vehicle_risk_lookup` | NHTSA safety history by make/model/year — recall campaigns and complaint stats |
59 
60## Quick start
61 
62```bash
63curl -s https://constat.dev/api/mcp \
64 -H 'content-type: application/json' \
65 -H 'accept: application/json, text/event-stream' \
66 -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
67 "params":{"name":"device_risk_lookup","arguments":{"product_code":"FRN"}}}'
68```
69 
70List tools with `{"method":"tools/list"}`. Note the `Accept` header must include
71`text/event-stream` (streamable-HTTP requirement).
72 
73Each of the 14 tools declares an output schema. Tool calls return structured
74content with an explicit `ok`, `not_found`, `invalid_request`, or `unavailable`
75status while preserving a text result for older clients.
76 
77The tools are observational and non-destructive, but advertise
78`readOnlyHint: false` because calls write bounded quota and operational-
79telemetry state. They do not publish or modify FDA, CMS, NHTSA, or other
80third-party records.
81 
82See the [integration guide](https://constat.dev/integrations), [architecture
83and trust boundaries](https://constat.dev/architecture), [privacy
84notice](https://constat.dev/privacy), and [support page](https://constat.dev/support).
85 
86## Related servers
87 
88- [Clarity MCP](https://github.com/thehealthai/clarity-mcp) — condition-aware
89 ingredient, product & supplement safety (verdict + evidence tier + citation).
90- [MCP Queen](https://github.com/mcpqueen/mcpqueen) — the graded MCP registry
91 that independently probes and grades this server.
92 
93## About
94 
95Built by [Health AI](https://healthai.com), the team behind
96[Constat](https://constat.dev). Informational only; verify against primary
97FDA/NHTSA sources.
98 
99## License
100 
101MIT — see [LICENSE](LICENSE).
102 

Discussion

Alternatives