Universal governance layer for AI agents. MCP-native, fail-closed, audit proofs and rollback.
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.
npm install dingdawg-governance
# 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:
{
"mcpServers": {
"dingdawg-governance": {
"command": "npx",
"args": ["dingdawg-governance"],
"env": {
"DINGDAWG_API_KEY": "your_key_here"
}
}
}
}
Get your free API key at app.dingdawg.com/settings/api.
| Tool | What it does |
|---|---|
validate_action | Pre-execution check. Returns APPROVED, FLAGGED, or BLOCKED with reason code and risk score. |
generate_receipt | Post-execution cryptographic receipt with tamper-evident output hash. |
capture_rollback_state | Snapshot current state before destructive or high-risk operations. |
rollback_action | Restore prior state from a receipt ID. |
query_receipts | Search receipts by date, agent, action type, or status. Export-ready. |
check_status | Current tier, daily usage, quota, and active governance alerts. |
generate_audit_report | On-demand compliance report — SOC 2, ISO 27001, or custom policy framework. |
| Plan | Governed actions/day | Rollback window | Audit reports |
|---|---|---|---|
| Free | 200 | — | — |
| Pro — $29/mo | 10,000 | 30 days | Unlimited |
| Business — $149/mo | Unlimited | 90 days | Compliance PDF |
No credit card to start. Full pricing: dingdawg.com/governance#pricing
Full docs at dingdawg.com/governance/docs
Issues and pull requests welcome. See CONTRIBUTING.md.
github.com/dingdawg/governance-mcp
Built by DingDawg — Trust layer for the agentic internet.
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
npx -y dingdawg-governanceMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-dingdawg-dingdawg-governance": {
"command": "npx",
"args": [
"-y",
"dingdawg-governance"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referencedingdawg-governancenpmio.github.dingdawg/dingdawg-governance works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.