Regulatory & Compliance Intelligence MCP

Regulatory & compliance intelligence for AI agents — rules, recalls, enforcement actions, and comment deadlines from free government sources, classified by industry and severity.

Part of the FoundryNet Data Network. Attest your agent's compliance analysis with MINT Protocol. See also: gov-contracts-mcp, brand-intel-mcp, patent-intel-mcp, financial-signals-mcp, weather-intel-mcp.

Live MCP endpoint (Streamable HTTP): https://compliance-mcp-production.up.railway.app/mcp

Tools

Free tier: 25 paid-tool queries/day per agent. Then x402: the tool returns an HTTP-402 with a Solana USDC payment memo — pay it, re-call with the same args plus payment_tx=<signature>. An Authorization: Bearer fnet_… key bypasses the paywall.

How it works

Every 12 hours the aggregator fetches new entries from Federal Register (rules/proposed/notices), openFDA (food/drug/device recall & enforcement), and CPSC (consumer product recalls), classifies each by industry (keyword taxonomy across 12 sectors) and severity (info → warning → action_required → critical), and stores them in a standalone Supabase project.

Severity logic: Class I / injury-or-death recalls + emergency rules → critical; final rules with a compliance deadline ≤ 90 days or enforcement penalties > $100K → action_required; proposed rules in comment period → warning; notices/guidance → info.

Honesty note: EPA ECHO, OSHA, and SEC enforcement (their public endpoints need multi-step queries or scraping) are planned additional sources; enforcement penalties are currently parsed from Federal Register notices.

Connect

Smithery: @foundrynet/compliance-intel · MCP registry: io.github.FoundryNet/compliance-mcp

{ "mcpServers": { "compliance": { "url": "https://compliance-mcp-production.up.railway.app/mcp" } } }

Built by FoundryNet · hello@foundrynet.io