QuantumGuard MCP Server - Post-quantum cryptography security tools for AI coding agents. Scan for quantum vulnerabilities, get migration templates, check NIST compliance.

Model Context Protocol (MCP) server that gives AI assistants and agents cryptography tools: key generation, encryption, ML-KEM, ML-DSA signing, hashing, streaming encryption, KMS and CBOM.

AI Agent, Instructions, Prompts, and MCP Servers, in a Go Post Quantum Cryptography project

MCP server for cryptography: hash (MD5/SHA), encode/decode (Base64/URL/hex), UUID/nanoid generator, password tools, JWT decoder Install: npx @rog0x/mcp-crypto-tools

Real-name identity for AI agents (国信智能体实名关联服务). Generates a local SM2 (Chinese national cryptography) keypair, links the agent to a real person via QR-code scan, claims a Verifiable Credential (VC), and generates/verifies SD-JWT Verifiable Presentations (VP) with selective disclosure. Also exposes SM2 sign/verify/encrypt/decrypt utilities. Keys and credentials never leave the machine — stored locally with SM4-CTR + SM3-HMAC encryption. 14 tools: identity_link, identity_status, identity_revoke, identity_vp, identity_verify_vp, vp_parse, vc_info, vc_raw, key_info, crypto_sign, crypto_verify, crypto_encrypt, crypto_decrypt, system_update. Runs locally via stdio (Node.js >= 18.13). Install: npm i -g realagent-mcp. Each agent requires a unique --agent-id (one agent-id = one identity = one SM2 keypair). Full docs: github.com/RedDateTech/RealAgentMCP

MCP SERVER

A SHA-256 correctness tester written in C, with MCP support for AI agents

A Multi-format Steganography Toolkit, with LLM integration

Identity and trust tools for AI agents — MCP server

A state-of-the-art cryptographically secure random number generator MCP server

Pure-Python MCP server for encoding, hashing, and crypto-primitives — computed for real, locally.

Production-ready MCP server for secure per-agent key management (Ed25519, ECDSA, and more) with a local file-based keystore.

Public ordered signed byte tape for autonomous-agent collaboration. Humans provide the physics; agents build everything else.

MCP server for AI agent identity verification via AIP — verify agents, check trust, sign content, exchange encrypted messages

Official TypeScript implementation of the IECC protocol. Features Ed25519 signing, RFC 8785 canonicalization, and AI-native verification via MCP.

QNSQY for Claude Code: post-quantum scanning, encryption and verification tools in a strict mode that never takes passwords or keys

QNSQY for Codex: post-quantum CBOM scan, encryption to public keys and verification on your own Linux computer. Takes no secrets.

Signed decision records for agent vendors facing customer evidence reviews. Public reference gateway and static verifier; pre-pilot, with documented limits.

The machine verifiable rights layer built for AI agents. Powered by Arbitrum, Model Context Protocol, and Supabase.

A security-focused Model Context Protocol server for GnuPG: sign, verify, encrypt, decrypt and manage keys without exposing private key material to the agent.

Open-source decoder that identifies an encoded string and unwraps every layer, with an MCP server so your coding agent decodes instead of guessing.

Cryptographic agent identity with Ed25519 anchors, signed action receipts, and scoped trust delegation. One .aid file. Any agent. Any LLM.

🔐 Cryptographic audit trails for AI decisions — hash chains, Merkle trees, RFC 3161 timestamps, compliance presets for HIPAA/GDPR/SOC2

Poseidon Merkle membership proofs, Groth16 zk-SNARK verification, Merkle Mountain Ranges, and EIP-712 hashing.

Free, open, account-free communication utility for agents — signed sessions, AEAD, replay protection, and MCP

Sentinel‑ThreatWall integrates an advanced C++ firewall with AI-based anomaly detection, providing comprehensive real-time analysis, reliable telemetry, and responsive network defense.

Zero-dependency Web Crypto suite & Model Context Protocol (MCP) server for AES-256-GCM, RSA-4096, and AI agent security.

Verify blockchain timestamp proofs offline (Python and Node CLI, MCP server), and create Polygon-anchored proofs through the ProofLedger API.

A local cryptographic inventory for developers and AI agents that carries verifiable coverage and its own limits inside the CBOM.

QNSQY for Gemini CLI and Antigravity CLI: post-quantum CBOM scan, encryption to public keys and verification on your own Linux computer. Takes no secrets.

Zero-telemetry steganography & visual cryptanalysis suite. Features MCP 2.0 Code Mode for AI agents, multi-detector steganalysis, and lossy-resilient modulation.

QuDAG Protocol (Quantum-Resistant DAG-Based Anonymous Communication System) - Claude Code implementation of a Test-Driven Development Implementation Plan for QuDAG Protocol with Claude Code

Signed receipts for the work your AI agent does. MCP server, SDK, CLI, dashboard and Magic Folder. Verify offline. Local-first, MIT.

Identity, continuity & trust for AI agents — prove you're an LLM (not human), hold a spirit key for signing/encryption/memory, and issue offline-verifiable signed documents.

Zero-dependency HTTP 402 fetch replacement for autonomous AI agents. EIP-3009 gasless USDC on Base. Buyer, seller, and MCP server.

Typed, bounded operations that puzzle-solving agents can discover, inspect and run. Ciphers, constraints, automata and exact checks via Python, a JSON CLI and MCP.

Chamber MCP: seal and open JSON with two keys. A license to seal new secrets is $20 a month or $200 a year. Opening takes both keys and costs nothing extra.

Local zero-egress MCP server configuration, CI/CD SARIF & CycloneDX 1.6 CBOM workflows for CipherMap (Claude Code, Cursor, Windsurf, GitHub Actions, GitLab CI)

Archive format built for AI agents: deterministic, content-addressed .tsr archives with per-file reads, grep and an MCP server, verified byte for byte. Rust, format v1 frozen.

🛡️ Multi-Platform Agent-First Secrets & Session Manager (Windows, macOS & Linux) in Go 1.26 Native — Envelope AES-256-GCM, VirtualLock/mlock, Native MCP Server (Claude & Antigravity), AWS Boto3 Emulator & OpenAPI 3.1

A verified runtime for trustworthy AI agents: every claim passes an 8-layer verification pipeline before it counts. Deterministic checks, explainable verdicts, no LLM judging an LLM. Pure C, zero dependencies, MCP-native.

SHULIAK SIP-1 v2.6.2: Zero-Egress AI & MCP Firewall (9/9 NIST SP 800-38G FF1 CAVP Verified, OWASP MCP05/06 Guard, EU AI Act AIBOM). CERN DOI: 10.5281/zenodo.24159380

The application workflow leverages AWS Lambda and Agentic AI to diagnose app issues—like network instability or expired tokens—with RS256 authentication. Smart recovery and crash-aware restart maintain user continuity, delivering a secure and reliable experience.

Open-source Rust zkVM for STARK-based verifiable computation, powered by Winterfell. Custom VM ISA with branching and registers, STARK prover/verifier, CLI, MCP server, HTTP proving API, CI proof gates, and on-chain attestation.

ACIS is a self-evolving cyber-immune system that uses telemetry and diagnostics to provide real-time, context-aware defense. Within seconds, it deploys digital antibodies, verifies each action with RS256, continuously simulates risk, and autonomously adapts to emerging threats.

ZMS (Zexio Secret Management System) is a high-performance, open-source secret management ecosystem. Featuring Blind Indexing, Shamir's Recovery Shards, and native Model Context Protocol (MCP) support. Built for developers who demand security without the complexity.

A spec‑driven readiness system using simulation, diagnostics, and agentic AI to produce explainable insights. Outputs include rule paths and RS256‑signed records. It models workload and risk to score readiness, surface bottlenecks, and improve clarity and consistency.

The Mathematics Universe: a 25-chapter engineering-mathematics core, 74 chapters across nine specialization tracks and a research frontier, and an appendix of proofs. Markdown + LaTeX Obsidian vault with Desmos graphs, crafted figures, a 1,400-page PDF and an MCP server.

TLS Cert Chain Resolver is a Go toolkit for building, validating, and inspecting TLS certificate chains. It ships with a CLI application, a composable Model Context Protocol (MCP) server, and helper libraries that emphasize memory efficiency and predictable output formats.

bag gives an AI agent a stable address and a durable mailbox, so agents belonging to different people, on different machines and accounts, can message each other safely. Every message is sealed for its recipient and signed by its sender. The relays in between carry envelopes they cannot open.