audit-ledger-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUDIT_API_URL | No | The base URL of the deployed audit ledger API (e.g., https://<api-id>.execute-api.<region>.amazonaws.com/prod) | |
| AUDIT_READ_KEY | No | Read API key for the tenant (used to verify and list decisions) | |
| AUDIT_WRITE_KEY | No | Write API key for the tenant (used to record decisions) | |
| AUDIT_TIMEOUT_MS | No | Timeout for API requests in milliseconds (default 5000) | |
| AUDIT_RETRY_ATTEMPTS | No | Number of retry attempts for API requests (default 3) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| record_decisionA | Record 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_decisionA | Verify 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. |
| list_decisionsA | List 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct and clear purpose: listing decisions, recording new decisions, and verifying integrity. No functional overlap.
All tool names follow a strict verb_noun pattern (list_decisions, record_decision, verify_decision), with consistent snake_case and action-object ordering.
Three tools perfectly cover the core audit ledger operations: create, read, and verify. The count is minimal yet complete for the domain.
The toolset covers the essential lifecycle of audit records: recording, listing, and verification. Update and delete are intentionally omitted to preserve immutability, so no gaps.