MCP SERVER · OFFICIAL PROJECTWrite an AI decision to an audit ledger — model version and hashed inputs recorded, so what was decided can be shown later.
LABSCO SUMMARY
The obvious design stores the prompt, and then the audit trail becomes a second copy of every piece of customer data the system ever saw — with the retention and disclosure obligations that follow. A hash proves the input was what someone later claims it was without holding it, which is the whole point of an audit record and none of the liability. Recording the model version alongside is the other necessary field: a decision is not reproducible without knowing which model made it, and model versions move underneath you. Four tools around one job — recording a decision and later proving the record is intact and complete — which most systems bolt on badly.
An audit ledger for AI decisions with four tools: one records a decision with its model version and a hash of its inputs, and three check and query what was recorded.
Nothing to try it: with no environment variables it writes to a shared public sandbox, which is not for real personal data. For production, a ledger you deploy yourself from shahidh68/audit-ledger, plus its URL and your write, read and HMAC keys.
One command — npx -y audit-ledger-mcp
USE CASES
Record the decision with its model version and hashed inputs at the moment it is made, rather than reconstructing it from logs later.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
list_decisionsList recorded AI decisions for the calling tenant within a time window. Returns newest first. The read key scopes the result to the caller's tenant — cross-tenant reads require an admin read key. Use this for compliance review, audit prep, or agent self-inspection of recent activity.
record_decisionRecord an AI decision to the audit ledger. Stores model version, hashed inputs, structured output, and human-review flag. The record is immutably sealed in S3 Object Lock for 7 years and queryable for the lifetime of the decision. Use this immediately after any AI decision that may need to be audited later — credit, hiring, fraud, customer routing, content moderation.
verify_completenessDetect whether any audit records have been deleted or omitted for the caller's tenant. Each successfully stored decision receives a per-tenant monotonic sequence number. This tool compares the ledger's counter against the rows actually present in DynamoDB and returns any sequence numbers that are missing. Use this when a regulator or compliance team asks 'can you prove the log is complete?' — verify_decision only proves an existing record was not altered; this proves no record has disappeared.
verify_decisionVerify a recorded AI decision has not been altered since it was written. The ledger fetches the queryable copy (DynamoDB) and the immutable copy (S3 Object Lock COMPLIANCE mode) independently and compares them. Returns integrity_verified=true if they match. Use this to satisfy a regulator request or to prove an audit trail to a compliance team.
BEFORE YOU INSTALL
4 tools when we connected. Without keys it runs against a public sandbox. In production, write keys cannot read and read keys cannot write: with only AUDIT_WRITE_KEY, record_decision works but verify_decision and list_decisions do not.
npx on PATH
CONTEXT COST
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y audit-ledger-mcp{
"mcpServers": {
"audit-ledger-sandbox": {
"command": "npx",
"args": [
"-y",
"audit-ledger-mcp"
]
}
}
}{
"mcpServers": {
"audit-ledger": {
"command": "npx",
"args": [
"-y",
"audit-ledger-mcp"
],
"env": {
"AUDIT_API_URL": "https://<YOUR_API_ID>.execute-api.<YOUR_REGION>.amazonaws.com/prod",
"AUDIT_WRITE_KEY": "<YOUR_AUDIT_WRITE_KEY>",
"AUDIT_READ_KEY": "<YOUR_AUDIT_READ_KEY>",
"AUDIT_HMAC_KEY": "<YOUR_AUDIT_HMAC_KEY>"
}
}
}
}This is the production setup: fill these in from the audit ledger you deployed (github.com/shahidh68/audit-ledger). Setting any of them switches sandbox mode off. To try the public sandbox instead, leave the env block out.
AUDIT_API_URL=<YOUR_AUDIT_API_URL> AUDIT_WRITE_KEY=<YOUR_AUDIT_WRITE_KEY> AUDIT_READ_KEY=<YOUR_AUDIT_READ_KEY> AUDIT_HMAC_KEY=<YOUR_AUDIT_HMAC_KEY> npx -y audit-ledger-mcpMCP servers
vaaraio
HMAKT99
ZentricProtocol
Rul1an