Back to Browse

Pg1 Ai Agent MCP Server

Developer ToolsUse Caution3.2MCP RegistryLocalRemote
Free

Server data from the Official MCP Registry

STIX 2.1 threat indicator feed: IPs, domains, URLs, file hashes from ThreatFox, OTX, NVD.

About

STIX 2.1 threat indicator feed: IPs, domains, URLs, file hashes from ThreatFox, OTX, NVD.

Remote endpoints: streamable-http: https://pg1-ai-agent.vercel.app/api/mcp

Security Report

3.2
Use Caution3.2High Risk

This MCP server exhibits multiple critical security vulnerabilities including unauthenticated access to sensitive operations, credential exposure via environment variables sent in API requests, arbitrary code execution via eval-like patterns, and overly permissive file operations on protected paths. The server lacks proper input validation, has incomplete authentication checks on dangerous operations, and implements a flawed approval system that can be bypassed. These issues represent a severe risk to system integrity and data confidentiality.

2 files analyzed · 17 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

How to Install & Connect

Available as Local & Remote

This plugin can run on your machine or connect to a hosted endpoint. during install.

Documentation

View on GitHub

From the project's GitHub README.

PG1 Sovereign Threat Intelligence API

Cryptographically-gated threat telemetry and IOC feeds for enterprise and autonomous nodes.

License Key Access: https://gikewun.gumroad.com/l/pg1-threat-intel-api

Two Ways to Connect

  • /api/ioc — simple REST GET, returns the STIX 2.1 indicator feed directly. Best for scripts, curl, and simple integrations.
  • /api/mcp — full Model Context Protocol server, 9 tools (CVE lookups, batch operations, threat actor dossiers, and more). Best for Claude, MCP-compatible agents, and any client speaking the MCP standard.

Both accept the same Gumroad license key via the x-api-key header, or per-call x402 micropayments ($0.01/call) via the X-PAYMENT/Payment-Signature header.

Free Tier (5 calls/day)

The free tier is opt-in — add x-free-tier: 1 to your request header. Without it, a request with no license key and no payment header returns 402 Payment Required by default.

curl -X GET "https://pg1-ai-agent.vercel.app/api/ioc" \
  -H "x-free-tier: 1"

Optional query parameters: ?since=<ISO timestamp>, ?type=<IPv4|domain|URL|FileHash-MD5|FileHash-SHA1|FileHash-SHA256>, ?min_score=<0-100>, ?limit=<1-1000>

Exception: get_ioc_context and get_ioc_batch (the pre-action safety-check tools) are always free when the result is found: false — no x-free-tier header needed for those specific "nothing on record" responses. The header is only required for the general free tier.

Installation & Connection (MCP Clients)

To connect your autonomous agent to the PG1 API, pass your Gumroad license key in the connection request.

Option 1: Via Smithery CLI

Run this command in your terminal, replacing the placeholder with your active key:

smithery mcp add --transport http --id pg1-threat-intel https://pg1-ai-agent.vercel.app/api/mcp --header "x-api-key: YOUR_GUMROAD_LICENSE_KEY"

Option 2: Free-tier test via curl (no key needed)

curl -X POST https://pg1-ai-agent.vercel.app/api/mcp \
  -H "Content-Type: application/json" \
  -H "x-free-tier: 1" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_cve_details",
      "arguments": { "cve_id": "CVE-2021-44228" }
    }
  }'

All Available MCP Tools

Call "method": "tools/list" against /api/mcp for full schemas. Summary:

ToolPurposeFree tier applies?
get_threat_indicatorsBulk STIX 2.1 indicator feedYes (needs x-free-tier: 1)
get_ioc_contextSingle-indicator safety checkAlways free if not found
get_ioc_batchUp to 20 indicators per callAlways free if none found
get_cve_detailsCVE lookup enriched with NVD, EPSS, CISA KEVYes (needs x-free-tier: 1)
get_cve_batchUp to 20 CVE IDs per callYes (needs x-free-tier: 1)
get_cve_by_productDiscover CVEs by vendor/productYes (needs x-free-tier: 1)
get_threat_actor_profileAPT/threat actor dossiers with MITRE ATT&CKYes (needs x-free-tier: 1)
get_usage_statusCheck your remaining free-tier quotaAlways free, no header needed
subscribe_alertsRegister a webhook for new matching indicatorsNo — license key required
submit_indicatorContribute an observed indicator for reviewNo — license key required

Acknowledgements

  • Frits (x402 Doctor): found the payment-gate ordering bug and confirmed the fix, so PG1 now returns a proper x402 payment challenge by default.

Reviews

No reviews yet

Be the first to review this server!