PROME Care Core is listed as active in the registry but did not answer our last check.
Check actions against fixed values using supplied numeric facts. Never authorizes or executes.
Over the last week it answered 2.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add care-core --transport http https://prome.ai/api/marketplace-mcp
{
"mcpServers": {
"care-core": {
"url": "https://prome.ai/api/marketplace-mcp"
}
}
}
[mcp_servers.care-core]
url = "https://prome.ai/api/marketplace-mcp"
{
"mcpServers": {
"care-core": {
"url": "https://prome.ai/api/marketplace-mcp"
}
}
}
{
"mcpServers": {
"care-core": {
"url": "https://prome.ai/api/marketplace-mcp"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://prome.ai/api/marketplace-mcp | streamable-http | answering | 580 ms | 9 min ago |
Agentic job hunt: scan careers pages, score against your resume, draft applications. Never applies.
Verify a proposed action against a signed Agent Mandate without executing or mutating accounts.
Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.
Authorize consequential AI agent actions before execution
Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Answers built from our own checks of this server.