Summary
This connects Claude to host firmware security checks that run below the OS level. You get five tools: scan_firmware reads BIOS, UEFI, TPM, and Secure Boot state; check_ant_signatures looks for NSA-ANT-class persistence preconditions; attest_firmware generates an HMAC-signed report verifiable at proofof.ai; gate_inference blocks or allows AI operations based on trust state; and list_threat_model shows what attack surface you're defending against. The design philosophy is honest indicator reporting rather than binary clean/compromised verdicts. Reach for this when you need hardware trust attestation before allowing inference on a machine, especially in sovereign AI or high-assurance deployments where firmware-level persistence is part of your threat model.
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Firmware Attestation MCP
Hardware trust layer for sovereign AI. Persistence implants live below the OS (BIOS/UEFI, SMM, network boot ROMs, HDD HPA) and survive OS reinstalls and disk wipes. This MCP attests a host's firmware trust state and gates inference on a verified result.
Tools
| Tool | What |
|---|---|
scan_firmware | read-only host evidence (Secure Boot, TPM, SIP, BIOS, HPA) |
check_ant_signatures | match to NSA-ANT-class persistence preconditions + defenses |
attest_firmware | HMAC-signed attestation, verifiable at proofof.ai/api/verify |
gate_inference | ALLOW/BLOCK AI on this host (strict by default) |
list_threat_model | the attack surface this defends against |
Honest by design
Reports indicators (preconditions implants rely on), never "clean". A BLOCK means "lacks confirmed trust anchors," not "hacked." Harden per the listed defenses, then re-gate.
pip install firmware-attestation-mcp
© CSOAI LTD (trading as MEOK AI Labs) · MIT
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"firmware-attestation-mcp": {
"command": "uvx",
"args": ["firmware-attestation-mcp"]
}
}
}
Or: pip install firmware-attestation-mcp then run the firmware-attestation-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
- "Use
scan_firmwareto …" - "Use
check_ant_signaturesto …" - "Use
attest_firmwareto …"
Part of the MEOK constellation
This MCP is one node in a connected ecosystem built by MEOK AI LABS around a single sovereign AI core — governed agents with a hash-chained audit trail, mapped to the CSOAI compliance charter.
- 🌐 The whole map: https://meok.ai/constellation
- 🛡️ AI governance & certification: https://councilof.ai · https://csoai.org
- ✅ Verify any signed report: https://meok.ai/verify
Featured
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →