PG1 Sovereign Threat Intelligence
warningspg1-ai-agent.vercel.app
STIX 2.1 threat indicator feed: IPs, domains, URLs, file hashes from ThreatFox, OTX, NVD.
https://pg1-ai-agent.vercel.app/api/mcpNo authMCP 2025-06-18v1.21.1last checked 4 Nov 2026spoke MCP on 100% of 89 checks (30 days)initialize in 161 msLast checked 4 Nov 2026
- ✓Answered the MCP handshake (MCP 2025-06-18)
- ✓Auth detected: No auth
- ✓Lists 21 tools
- !1 warning
- ✓Spoke MCP on 89 of 89 checks (30 days)
Will my client connect?
Decided from what the probe found at the endpoint, and from what each client's own documentation says it can complete. Every row carries the day that documentation was read.
✓Claude CodeConnects
The endpoint answers an anonymous handshake, so no credential is needed.
claude mcp add --transport http pg1-sovereign-threat-intelligence https://pg1-ai-agent.vercel.app/api/mcpClaude Code docs · read on 2026-08-30
✓Claude (claude.ai & Desktop)Connects
The endpoint answers an anonymous handshake, so no credential is needed.
Settings → Connectors → Add custom connector, then paste https://pg1-ai-agent.vercel.app/api/mcp.
Claude (claude.ai & Desktop) docs · read on 2026-08-30
✓ChatGPTConnects
The endpoint answers an anonymous handshake, so no credential is needed.
Settings → Apps → Advanced settings → Developer mode, then create a connector pointing at https://pg1-ai-agent.vercel.app/api/mcp.
ChatGPT docs · read on 2026-08-30
✓CursorConnects
The endpoint answers an anonymous handshake, so no credential is needed.
{
"mcpServers": {
"pg1-sovereign-threat-intelligence": {
"url": "https://pg1-ai-agent.vercel.app/api/mcp"
}
}
}Cursor docs · read on 2026-08-30
✓VS Code (Copilot)Connects
The endpoint answers an anonymous handshake, so no credential is needed.
{
"servers": {
"pg1-sovereign-threat-intelligence": {
"type": "http",
"url": "https://pg1-ai-agent.vercel.app/api/mcp"
}
}
}VS Code (Copilot) docs · read on 2026-08-30
How to authenticate
Checked against the endpoint by our probe on 4 Nov 2026. These are the capabilities the server advertises, not a prediction about any particular client.
| Scheme | No auth |
|---|---|
| Protected-resource metadata | ✕Not found Without it a client has to guess where the authorization server lives. |
| Anonymous access | Handshake succeeds; 21 tools listable |
| Credentials demanded in prose | ✕check_hostname_reputation, check_wallet_age, check_ip_abuse, check_package These tools are listed anonymously and their own descriptions ask for an account or key, but no challenge is issued — so a client has nothing to act on and the refusal arrives as a tool error. |
What the probe found
4 of the 21 tools listed anonymously say in their own descriptions that they need an account or a key (check_hostname_reputation, check_wallet_age, check_ip_abuse, check_package), but the endpoint issued no WWW-Authenticate challenge. The requirement is stated only in prose, so a call reaches the tool and comes back as a tool error instead of an authorization step.
Neither the reserved <endpoint>/server-card location nor the domain's /.well-known/ai-catalog.json describes this endpoint (SEP-2127), so a client that discovers servers by domain will not find it.
Tools
Contract history
Instructions rewritten: get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: check_agent_card, check_x402_endpoint, preflight_check. The description an agent follows changed; the callable contract may not have.
Breaking: subscribe_alerts
Instructions rewritten: get_cve_batch, get_cve_by_product, get_cve_details, get_ioc_batch, get_ioc_context, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_ioc_batch, get_ioc_context, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_ioc_batch, get_ioc_context, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_cve_batch, get_cve_by_product, get_cve_details, get_ioc_batch, get_ioc_context, get_threat_actor_profile, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_cve_batch, get_cve_by_product, get_cve_details, get_ioc_batch, get_ioc_context, get_threat_actor_profile, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_cve_batch, get_cve_by_product, get_cve_details, get_ioc_batch, get_ioc_context, get_threat_actor_profile, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_cve_batch, get_cve_details, get_ioc_context, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Instructions rewritten: get_cve_details, get_threat_indicators. The description an agent follows changed; the callable contract may not have.
Breaking: get_threat_indicators
Watch this server
Save its public contract as a baseline and manage breaking-change email alerts.
Set up a watchRoute it through the gateway
Put this endpoint behind one find_tools / call_tool pair with the rest of your servers. Part of Pro.
Add to my gatewayOwn this server?
Sign in to claim this listing by proving control of its host.
Sponsor this listing
Pins it in a sponsor slot on the directory front page for 30 days, labelled Sponsored.
Sign in to sponsor · $59 / 30 daysStatus badge
Status for a README, from the last probe — cached an hour, so up to seven hours behind the endpoint. Links back to this page.
[](https://mcpi.app/servers/pg1-sovereign-threat-intelligence)<a href="https://mcpi.app/servers/pg1-sovereign-threat-intelligence"><img src="https://mcpi.app/servers/pg1-sovereign-threat-intelligence/badge.svg" alt="MCP status" height="20"></a>