Qeaas MCP is listed as active in the registry but did not answer our last check. It exposes 6 tools. Last commit 15 Sep 2026.
QRNG-seeded random bytes, seeds, and ML-KEM-768 keys with signed provenance receipts.
We read the source, 15 h ago · tools taken from the live server · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
<select name="user_type">
<option value="standard" {% if u.profile.user_type == "standard" %}selected{% endif %}>
path = os.path.join(OUTPUT_DIR, f"calib_{backend.name}_{ts}.json")
subprocess.run(cmd, check=True)
row.innerHTML = tiles.map(t =>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.
claude mcp add qeaas-mcp --transport http https://api.qeaas.eu/mcp
{
"mcpServers": {
"qeaas-mcp": {
"url": "https://api.qeaas.eu/mcp"
}
}
}
[mcp_servers.qeaas-mcp]
url = "https://api.qeaas.eu/mcp"
{
"mcpServers": {
"qeaas-mcp": {
"url": "https://api.qeaas.eu/mcp"
}
}
}
{
"mcpServers": {
"qeaas-mcp": {
"url": "https://api.qeaas.eu/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
kem_encapsulate
kem_keypair
random
random_bytes
dice
verify
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.qeaas.eu/mcp | streamable-http | answering | 20 ms | 15 min ago |
Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.
Signed, hash-chained provenance receipts for AI agent actions.
Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
Reviewed public-data search and execution with provenance and verifiable integrity receipts.
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
Governance runtime for AI agents with signed provenance, compliance audits, and OSINT.
Policy-gated agent spend with signed receipts and rail-extract audit
Verified behind-the-meter data center power, announcements, and provenance receipts.
Answers built from our own checks of this server.