Dingdawg Governance
This is an audit and policy enforcement layer that wraps around your MCP-enabled AI agents. It exposes seven tools: validate_action runs pre-execution policy checks, generate_receipt creates cryptographic proofs of what happened, capture_rollback_state and rollback_action let you undo file writes, query_receipts searches your history, and generate_audit_report exports compliance docs. You'd use this if you need tamper-evident logs of every file write and shell command your agent executes, or if you're working in a regulated environment where you need rollback capability and SOC 2 style reporting. Requires a DingDawg API key. Free tier covers 200 governed actions per day.
- GitHub stars
- 1
- tools
- 7
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- May 26, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
validate_actionPre-execution check. Returns APPROVED, FLAGGED, or BLOCKED with reason code and risk score.
Pre-execution check. Returns APPROVED, FLAGGED, or BLOCKED with reason code and risk score.
No parameter schema in public metadata yet.
generate_receiptPost-execution cryptographic receipt with tamper-evident output hash.
Post-execution cryptographic receipt with tamper-evident output hash.
No parameter schema in public metadata yet.
capture_rollback_stateSnapshot current state before destructive or high-risk operations.
Snapshot current state before destructive or high-risk operations.
No parameter schema in public metadata yet.
rollback_actionRestore prior state from a receipt ID.
Restore prior state from a receipt ID.
No parameter schema in public metadata yet.
query_receiptsSearch receipts by date, agent, action type, or status. Export-ready.
Search receipts by date, agent, action type, or status. Export-ready.
No parameter schema in public metadata yet.
check_statusCurrent tier, daily usage, quota, and active governance alerts.
Current tier, daily usage, quota, and active governance alerts.
No parameter schema in public metadata yet.
generate_audit_reportOn-demand compliance report — SOC 2, ISO 27001, or custom policy framework.
On-demand compliance report — SOC 2, ISO 27001, or custom policy framework.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
DINGDAWG_API_KEYsecretAPI key for paid tier access — get free at dingdawg.com
Readme
DingDawg Governance
Every AI action receipted. Capability-gated. Rollback-ready.
AI Governance-as-a-Service via MCP. Every write, shell command, and state-changing operation your agent makes is validated before it runs and cryptographically receipted after it completes — giving you a tamper-evident audit trail you can query, export, or roll back at any time.
Works with Claude Code, Codex, Cursor, Windsurf, and any MCP-compatible agent.
Install
npm install dingdawg-governance
Quick Start
# Authenticate (free — no credit card)
npx dingdawg-governance auth login
# Start the governance MCP server
DINGDAWG_API_KEY=your_key npx dingdawg-governance
Add to your MCP client config:
Details
- Repository
- github.com/dingdawg/dingdawg-governance
- Package
dingdawg-governance- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active