Cryptair MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 8 May 2026.
Tamper-evident attestation tools for AI agents — on-chain receipts on Hedera Hashgraph mainnet.
Today is the operative word: we check Cryptair MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cryptair-mcp-server -- npx -y @cryptair/mcp-server
{
"mcpServers": {
"cryptair-mcp-server": {
"args": [
"-y",
"@cryptair/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.cryptair-mcp-server]
command = "npx"
args = ["-y", "@cryptair/mcp-server"]
{
"mcpServers": {
"cryptair-mcp-server": {
"args": [
"-y",
"@cryptair/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"cryptair-mcp-server": {
"args": [
"-y",
"@cryptair/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
CRYPTAIR_API_KEY (Optional. Pre-configured Cryptair API key. If unset, the agent can call register_agent at runtime to self-register and the key is silently stored at ~/.cryptair/credentials.json.), CRYPTAIR_EMAIL (Optional. Email used as fallback when submit_attestation auto-provisions a counterparty account.), CRYPTAIR_BASE_URL (Optional. Override the API base URL for self-hosted or staging environments. Defaults to https://www.cryptair.io.).
The author declared them in the registry entry; get the values from the project itself.
Tamper-evident action receipts, trust scoring & capability tokens for AI agents. 29 MCP tools.
Mint tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Decay-weighted reputation + tamper-evident trust attestations for the agent economy.
Signed, hash-chained provenance receipts for AI agent actions.
Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.
25 x402 paid API tools for AI agents on Base mainnet.
Answers built from our own checks of this server.