Sphior AI Governance MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 11 installs a week from npm. Last commit 20 Oct 2026.
Record what your AI did as tamper-evident evidence for ISO 42001, EU AI Act and SOC 2. Hash-only.
Today is the operative word: we check Sphior AI Governance MCP 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 sphior-ai-governance-mcp -e 'SPHIOR_AIGOV_TOKEN=<SPHIOR_AIGOV_TOKEN>' -- npx -y sphior-ai-governance-mcp
{
"mcpServers": {
"sphior-ai-governance-mcp": {
"command": "npx",
"args": [
"-y",
"sphior-ai-governance-mcp"
],
"env": {
"SPHIOR_AIGOV_TOKEN": "<SPHIOR_AIGOV_TOKEN>"
}
}
}
}
[mcp_servers.sphior-ai-governance-mcp]
command = "npx"
args = ["-y", "sphior-ai-governance-mcp"]
env = { SPHIOR_AIGOV_TOKEN = "<SPHIOR_AIGOV_TOKEN>" }
{
"mcpServers": {
"sphior-ai-governance-mcp": {
"command": "npx",
"args": [
"-y",
"sphior-ai-governance-mcp"
],
"env": {
"SPHIOR_AIGOV_TOKEN": "<SPHIOR_AIGOV_TOKEN>"
}
}
}
}
{
"servers": {
"sphior-ai-governance-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"sphior-ai-governance-mcp"
],
"env": {
"SPHIOR_AIGOV_TOKEN": "<SPHIOR_AIGOV_TOKEN>"
}
}
}
}
Put your own value in place of
<SPHIOR_AIGOV_TOKEN> (Ingestion token for your SPHIOR account. Without it the server still starts and tells you how to create one; no events are recorded until it is set. Create one at https://sphior.com/app?settings=aigov).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
SPHIOR_AIGOV_ENDPOINT (Override the ingestion endpoint for self-hosted / regional deployments. Default: https://sphior.com/api/ai-governance/ingest).
AI governance evidence for EU AI Act, ISO 42001, SOC 2, and NIST AI RMF.
EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
Tamper-evident record of what your AI agent did, plus local-first verifiable memory.
Read, verify and export a tamper-evident log of what an AI agent did. Read-only.
Tamper-evident evidence log: signed heads, proofs, and recording salted digests of your records.
Signed, hash-chained, tamper-evident AI incident records. EU AI Act Article 73 serious-incident repo
Tamper-evident audit trails for AI agents — Ed25519-signed, hash-chained, EU AI Act ready.
GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish.
Answers built from our own checks of this server.