Post-Quantum Cryptography MCP Server

Overview Schema Source Related Servers Discussions Admin

pqc_hybrid_seal

Encrypts UTF-8 or base64 plaintext using hybrid X25519, ML-KEM-768, and AES-256-GCM in an anonymous sealed-box format for research and prototyping.

Instructions

Encrypt plaintext using hybrid X25519 + ML-KEM-768 + AES-256-GCM. Anonymous sealed-box. Research/prototyping only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pqc_hybrid_seal"
  }
}

Input Schema

Name	Required	Description
`plaintext`	No	UTF-8 string to encrypt (mutually exclusive with plaintext_base64)
`plaintext_base64`	No	Base64-encoded binary data (mutually exclusive with plaintext)
`recipient_key_store_name`	No	Name of stored hybrid key bundle
`recipient_pqc_public_key`	No	Base64-encoded ML-KEM-768 public key
`recipient_classical_public_key`	No	Base64-encoded raw 32-byte X25519 public key

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.10.0Nov 4, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It helpfully discloses the algorithm stack, the anonymity property (no sender authentication) and a research-only caveat, which is real behavioral context. It does not say what is returned, whether a nonce/header is prepended, or that the recipient must possess both key halves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, algorithm stack front-loaded, safety caveat last. No filler and nothing redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should indicate what the caller receives (e.g. base64 sealed box) and how it maps to the corresponding open tool. The rich input schema offsets some of this, but the return side is entirely unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every parameter carries its own description, including the base64 mutual-exclusion note. The description adds no meaning beyond the schema, which is acceptable at full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (encrypt) and resource (plaintext) and pins down the exact construction (X25519 + ML-KEM-768 + AES-256-GCM) plus the mode ('anonymous sealed-box'). The word 'anonymous' implicitly separates it from the sibling pqc_hybrid_auth_seal, but that sibling is never named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Anonymous sealed-box' and 'Research/prototyping only' imply when this is appropriate, and the contrast with the auth_seal siblings is inferable. However, there is no explicit statement of when to choose this over pqc_hybrid_auth_seal or what makes the research-only restriction binding.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.