{
"mcpServers": {
"qu3-app": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Quantum-proof MCP Server and Client Interactions
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 296 days ago. 51 stars.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Qu3 App and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
This project provides a client application (qu3-app) for secure interaction with Quantum-Safe Multi-Compute Provider (MCP) environments. It leverages post-quantum cryptography (PQC) standards for establishing secure communication channels, ensuring client authenticity, and verifying server attestations.
This client is designed to work with MCP servers that support the QU3 interaction protocols. For development and testing, a compatible mock server implementation is included in scripts/mock_mcp_server.py.
The following diagram illustrates the end-to-end secure communication pattern implemented between the QU3 Client and the MCP Server:
sequenceDiagram
participant Client as QU3 Client (CLI)
participant Server as MCP Server
Note over Client,Server: Initial Setup (First Run / Keys Missing)
Client->>+Server: GET /keys (Fetch Server Public Keys)
Server-->>-Client: Server KEM PK, Server Sign PK (Base64)
Client->>Client: Store Server Public Keys Locally
Note over Client,Server: Establish Secure Session
Client->>+Server: POST /kem-handshake/initiate { Client KEM PK, Client Sign PK }
Server->>Server: Encapsulate Shared Secret (using Client KEM PK)
Server->>Server: Derive AES-256 Session Key & Store Session Details
Server-->>-Client: { KEM Ciphertext }
Client->>Client: Decapsulate Shared Secret & Derive AES-256 Session Key
Client->>Client: Store AES Session Key
Note over Client,Server: Secured Inference Request
Client->>Client: Prepare Secure Request (Sign Payload, Encrypt with AES Key)
Client->>+Server: POST /inference { Client KEM PK, nonce, ciphertext }
Server->>Server: Process Secure Request (Lookup Session, Validate Timestamp, Decrypt, Verify Signature)
Server->>Server: Execute Model(input_data) -> output_data
Server->>Server: Prepare Secure Response (Prepare Attestation, Sign, Encrypt with AES Key)
Server-->>-Client: { resp_nonce, resp_ciphertext }
Client->>Client: Process Secure Response (Decrypt, Verify Attestation)
Client->>Client: Process Result
Note over Client,Server: Secured Policy Update
Client->>Client: Prepare Secure Policy (Read, Sign, Encrypt with AES Key)
Client->>+Server: POST /policy-update { Client KEM PK, policy_nonce, policy_ciphertext, policy_sig }
Server->>Server: Process Secure Policy (Lookup Session, Validate Timestamp, Decrypt, Verify Signature)
Server->>Server: Process Policy (Mock)
Server->>Server: Prepare Secure Status (Sign Status, Encrypt with AES Key)
Server-->>-Client: { status_nonce, status_ciphertext, status_sig }
Client->>Client: Process Secure Status (Decrypt, Verify Signature)
Client->>Client: Display Status
This diagram shows how the main Python modules within the client application interact:
graph TD
A("User CLI (Typer)") --> B("src_main");
B -- Initiates --> C("src_mcp_client (MCPClient)");
B -- Uses --> D("src_config_utils");
C -- Uses --> E("src_pqc_utils");
C -- Uses --> G("requests Session");
D -- Uses --> H("PyYAML");
D -- Manages --> I("Key Files");
D -- Uses --> G;
E -- Uses --> J("liboqs_python");
E -- Uses --> K("cryptography");
subgraph Cryptography
J
K
end
subgraph Networking
G
end
subgraph "Configuration & Keys"
H
I
end
Keys are crucial for the security protocols. Here's how they are managed:
graph LR
subgraph Client Side
A["CLI: generate-keys"] --> B{"src_main.py"};
B --> C["src_pqc_utils.py"]:::pqc --> D{"Generate KEM/Sign Pairs"};
D --> E["src_config_utils.py"]:::config --> F["Save Client Keys (.pub, .sec)"];
G["CLI: run-inference/etc."] --> B;
B --> H{"Initialize Client"};
H --> E --> I{"Load Clie
... [View full README on GitHub](https://github.com/qu3ai/qu3-app#readme)