MCP server: One MCP server.

Dingdawg Governance

@dingdawgMCP server · External

Universal governance layer for AI agents. MCP-native, fail-closed, audit proofs and rollback.

AI agent governancev2.1.6MITJavaScript
Freeno charge per call

Runs on your machine from its package; the steps are below.

What it does

  1. Reads
  2. Writes
  3. High impact

At most: moves money, runs code or commands, deletes data, or sends messages for you.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

npmdingdawg-governancev2.1.6

Run

npx -y dingdawg-governance

MCP client config

{
  "mcpServers": {
    "dingdawg-governance": {
      "command": "npx",
      "args": [
        "-y",
        "dingdawg-governance"
      ]
    }
  }
}
README2 min read

npm version npm downloads License: MIT

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

bash
npm install dingdawg-governance

Quick Start

bash
# 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:

json
{
  "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.


What You Get

  • Pre-execution validation — Every action checked against your policy before it runs. Blocked actions never touch your filesystem.
  • Cryptographic receipts — Tamper-evident record for every action with a unique ID, output hash, and public verification URL.
  • One-command rollback — Undo any file write by referencing its receipt ID. Prior state is captured automatically before every write.
  • Real-time trust scores — Behavioral pattern tracking across sessions surfaces anomalies before they become incidents.
  • Compliance reports in seconds — SOC 2 and ISO 27001-aligned audit reports as signed PDF or structured JSON. One API call.

MCP Tools

ToolWhat it does
validate_actionPre-execution check. Returns APPROVED, FLAGGED, or BLOCKED with reason code and risk score.
generate_receiptPost-execution cryptographic receipt with tamper-evident output hash.
capture_rollback_stateSnapshot current state before destructive or high-risk operations.
rollback_actionRestore prior state from a receipt ID.
query_receiptsSearch receipts by date, agent, action type, or status. Export-ready.
check_statusCurrent tier, daily usage, quota, and active governance alerts.
generate_audit_reportOn-demand compliance report — SOC 2, ISO 27001, or custom policy framework.

Plans

PlanGoverned actions/dayRollback windowAudit reports
Free200——
Pro — $29/mo10,00030 daysUnlimited
Business — $149/moUnlimited90 daysCompliance PDF

No credit card to start. Full pricing: dingdawg.com/governance#pricing


Documentation

Full docs at dingdawg.com/governance/docs


Contributing

Issues and pull requests welcome. See CONTRIBUTING.md.

github.com/dingdawg/governance-mcp


Built by DingDawg — Trust layer for the agentic internet.

Similar modules

Browse AI agent governance