PQC Khepra MCP Server: Agentic Security Attestation Framework
@nouchix
About PQC Khepra MCP Server: Agentic Security Attestation Framework
KHEPRA MCP Server
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"khepra": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"KHEPRA_MODE=sovereign",
"-v",
"/var/lib/khepra:/var/lib/khepra",
"ghcr.io/nouchix/pqc-khepra-mcp:latest"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is PQC Khepra MCP Server?
It is a sovereign compliance engine that connects AI assistants directly to a hardened security attestation framework. It bundles 36,195 STIG/CCI/NIST/CMMC mappings and provides post-quantum cryptographic attestation on every tool call. Designed for air-gapped, DoD, and classified environments, it runs on your own metal with zero token costs.
How to use PQC Khepra MCP Server?
Install via Docker (recommended) or compile a binary with Go 1.21+. Configure your MCP client (Claude Desktop, Cursor, VS Code, Windsurf, Continue.dev) using a stdio subprocess command pointing to the server. Set environment variables like KHEPRA_MODE=sovereign and optionally KHEPRA_LICENSE_KEY for paid tiers. Run the pqc_stig tool (Community tier) to assess quantum readiness against the built-in PQC-01-STIG-V1R1.
Key features of PQC Khepra MCP Server
- 36,195 offline STIG/CCI/NIST/CMMC mappings
- Post-quantum cryptographic attestation (ML-DSA-65 / FIPS 204)
- World's First DoD PQC STIG (17 controls)
- Godfather Report with dollar-denominated business impact (FAIR model)
- Air-gap and SCIF compatible (sovereign/ironbank modes)
- Flat annual licensing – no per-token charges
- Runs on your metal – on-prem, classified environments
Use cases of PQC Khepra MCP Server
- Assess a project’s quantum readiness against PQC-01-STIG-V1R1
- Generate executive-ready risk reports for compliance audits
- Scan systems in air-gapped or classified networks
- Map security findings to STIG, NIST 800-53/800-171, or CMMC controls
- Operate a zero-egress compliance engine inside a SCIF
FAQ from PQC Khepra MCP Server
Do I need a license key for the Community tier?
No. The Community tier is free and requires no license key – just run pqc_stig with KHEPRA_MODE=sovereign.
Can this server run without internet access?
Yes. In sovereign mode the server makes zero egress calls, making it suitable for air-gapped and SCIF environments.
What MCP clients does it support?
Claude Desktop, Cursor, VS Code (Cline extension), Windsurf, and Continue.dev. Cloud tools (Claude.ai, ChatGPT, Gemini) can connect via
Frequently asked questions
Do I need a license key for the Community tier?
No. The Community tier is free and requires no license key – just run `pqc_stig` with `KHEPRA_MODE=sovereign`.
Can this server run without internet access?
Yes. In sovereign mode the server makes zero egress calls, making it suitable for air-gapped and SCIF environments.
What MCP clients does it support?
Claude Desktop, Cursor, VS Code (Cline extension), Windsurf, and Continue.dev. Cloud tools (Claude.ai, ChatGPT, Gemini) can connect via
Basic information
More Developer Tools MCP servers

Codex Pets
astandrikPublic read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.

Windframe
Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp
TranscriptFetch MCP Server
TranscriptFetchModel Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.

Foremerge
naw103Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

discoverGPT
Joe MonastierodiscoverGPT is visualAI's unified MCP gateway for AI commerce, exposing 29 tools across four capabilities on one canonical product catalog: trimodal search (natural-language, precise-color, and image-similarity), AI cata
Comments