PopHIVE for AI agents

PopHIVE is Yale's harmonized US public health surveillance dataset covering disease, vaccination, and health outcome trends. Researchers and public health teams use it to track population health signals. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

AnalyticsNo authMCP + RESTpophive.org
AUDIT LOG · POPHIVEPOLICY: acme-support
09:41:07 · claude · u_8f2read
pophive.get_map
Get map✓ allowed · 212ms
09:41:08 · claude · u_8f2read
pophive.compare
Compare✓ allowed · 164ms
EVERY POPHIVE CALL, ON THE RECORD
01 · USE CASES

What agents do in PopHIVE.

01

Check a health trend over time

Pull a trend for a tracked health indicator to see how it has changed over months.

02

Compare regions on an indicator

Compare health outcome data across regions to spot where a signal is rising fastest.

03

Get current status read-only

Look up the current status of a tracked disease or vaccination indicator, read-only.

02 · ACTIONS

7 PopHIVE actions, graded by risk.

Every PopHIVE action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

7

Look things up. Allowed by default.

  • pophive.get_map
    Get map
  • pophive.get_data
    Get data
  • pophive.get_trend
    Get trend
  • pophive.get_coverage
    Get coverage
  • pophive.get_overview
    Get overview
  • pophive.get_current_status
    Get current status
  • pophive.compare
    Compare

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

PopHIVE in three steps.

  1. 01Your users connect PopHIVEThey add their PopHIVE no auth on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls PopHIVE through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('pophive', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How PopHIVE connects.

PopHIVE needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

The same PopHIVE connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
No auth
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use PopHIVE from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

PopHIVE and Arc0, answered.

Q01

Can I use PopHIVE with Claude, ChatGPT or Cursor?

Yes. Connect PopHIVE to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the PopHIVE actions you allow.

Q02

How do users connect PopHIVE?

PopHIVE needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.

Q03

Which PopHIVE actions can my agent take?

7 in total: 7 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in PopHIVE?

Yes. Allow read actions and deny writes in the PopHIVE policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call PopHIVE too?

Yes. The same PopHIVE connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug PopHIVE into your agent.

Your users connect PopHIVE once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan