qeaas-mcp by qeaas.eu

MCP server · indexed, not reviewed

Hostedvendor's own

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

QRNG-seeded random bytes, seeds, and ML-KEM-768 keys with signed provenance receipts.

What the official MCP registry says

Facts

MCP registry
eu.qeaas/qeaas-mcp · 1.0.0
Endpoint
https://api.qeaas.eu/mcp
Website
qeaas.eu
GitHub stars
2
Registry entry
updated 28 Jul 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under qeaas.eu, a namespace the registry only gives to whoever proves they control that domain.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 6 · about 577 tokens of context · checked 1 hour ago

ToolWhat it doesHint
randomDRBG-derived random bytes (base64), anonymous and rate-limited. Capped at 64 bytes/request; powers the public dice player.
diceRejection-sampled dice rolls (no modulo bias), anonymous and rate-limited. Echoes the DRBG bytes drawn for transparency.
random_bytesCanonical developer endpoint: DRBG-derived bytes in hex or base64 with a signed provenance receipt. Requires X-API-Key; 32..4096 bytes; per-key rate limit + daily quota.
verifyVerify the provenance of an issued value from its request_id and/or receipt. Provenance only -- never a value-confirmation oracle. Anonymous, rate-limited.
kem_keypairGenerate an ML-KEM-768 (Kyber, post-quantum) keypair seeded from the QRNG->DRBG chain. Public key always returned; secret key only for the demo flow (loud demo-only note). Requires X-API-Key.
kem_encapsulateEncapsulate against a supplied ML-KEM-768 public key to produce a ciphertext (and, for the demo, the shared secret). Requires X-API-Key.

What https://api.qeaas.eu/mcp answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 12 warnings · 2 notes

  • warnTC11dicenone of its 2 parameters has a description
  • warnTC11kem_encapsulatenone of its 2 parameters has a description
  • warnTC11kem_keypairits one parameter, include_secret_key, has no description
  • warnTC11randomits one parameter, bytes, has no description
  • warnTC11random_bytesnone of its 2 parameters has a description
  • warnTC11verifynone of its 2 parameters has a description
  • warnTC16diceno readOnlyHint or destructiveHint
  • warnTC16kem_encapsulateno readOnlyHint or destructiveHint
  • warnTC16kem_keypairno readOnlyHint or destructiveHint
  • warnTC16randomno readOnlyHint or destructiveHint
  • warnTC16random_bytesno readOnlyHint or destructiveHint
  • warnTC16verifyno readOnlyHint or destructiveHint
  • noteTC24server6 of 6 tools have no outputSchema
  • noteTC29serverabout 40 tokens (6% of the definitions) are titles that repeat property or function names

The checks from /check and anchor check, run each day on the list above: about 577 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.