# io.github.dingdawg/dingdawg-governance (npm · dingdawg-governance)

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

- Trust score: 63/100 (medium)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `dingdawg-governance`: 63/100 (this document), [markdown](https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance.md), [page](https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance)

## Channel facts

- Registry: `npm`
- Package: `dingdawg-governance`
- Version: `2.1.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 18 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 894 tokens (~127/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add dingdawg-dingdawg-governance -- npx -y dingdawg-governance
```

### Codex

```bash
codex mcp add dingdawg-dingdawg-governance -- npx -y dingdawg-governance
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dingdawg-dingdawg-governance": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "dingdawg-governance"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dingdawg-dingdawg-governance --command npx --arg -y --arg dingdawg-governance
```

### Hermes

```yaml
mcp_servers:
  dingdawg-dingdawg-governance:
    command: "npx"
    args: ["-y", "dingdawg-governance"]
```

### Other

```json
{
  "mcpServers": {
    "dingdawg-dingdawg-governance": {
      "command": "npx",
      "args": [
        "-y",
        "dingdawg-governance"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 63, +10)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [functional regression] License: fail → unverified
- [functional regression] Maintenance: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional] Licence: BUSL-1.1

### 2026-08-01 (score 53, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 63, +37)

- [security regression] Provenance: unverified → fail
- [security regression] Malware scan: pass → unverified
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional regression] License: unverified → fail
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Maintenance: unverified → pass
- [functional] Licence: BUSL-1.1
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 26, −20)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (7)

### `govern_action` (~173 tokens)

Govern any AI agent action. Performs capability check + policy evaluation + generates a governance receipt. Returns a receipt proving the action was governed. When API key is set, uses cloud API with local fallback.

Input parameters:

- `action_description` (string, required): Human-readable description of what the agent is about to do
- `action_type` (string, required): Type of action (e.g., 'send_email', 'make_purchase', 'modify_data', 'api_call')
- `agent_id` (string, required): Identifier for the AI agent performing the action
- `context` (object): Additional context key-value pairs for policy evaluation
- `risk_tier` (string): Self-assessed risk level of this action
- `target_resource` (string): The resource being acted upon (e.g., 'user_database', 'email_server', 'payment_api')

### `get_verified_badge` (~98 tokens)

Returns the 'Powered by DingDawg Verified' badge payload for a governed action receipt. Creators can opt-in to emit this badge in agent output — every governed action receipt includes a verifiable badge URL, turning governed agents into DingDawg marketing channels. Pass the receipt_id returned by govern_action.

Input parameters:

- `receipt_id` (string, required): Receipt ID returned by a govern_action call (e.g. 'gov_abc123_def456')

### `audit_trail` (~91 tokens)

Get the governance audit trail. Returns governance receipts from local storage or cloud API. Free to use.

Input parameters:

- `agent_id` (string): Agent ID to get all governed actions for
- `limit` (number): Maximum number of records to return (default 10)
- `receipt_id` (string): Receipt ID from a govern_action call
- `time_range` (string): Time range for audit trail lookup

### `compliance_check` (~116 tokens)

Quick compliance check against common AI governance frameworks. Free tier: 10 checks per day. Evaluates against EU AI Act, Colorado AI Act — Revised (SB26-189 / ADMT, eff. Jan 1 2027), NIST AI RMF, and ISO 42001.

Input parameters:

- `deployment_stage` (string): Current deployment stage
- `framework` (string): Framework to check against (default: all)
- `system_description` (string, required): Describe your AI system: what it does, data sources, decision scope

### `meter_llm_call` (~166 tokens)

Track the cost of an LLM API call and enforce budget limits. Call this after every LLM API response. Returns real-time cost, cumulative spend, and budget status. Free to use — no API key required.

Input parameters:

- `agent_id` (string, required): Unique identifier for the agent making the LLM call
- `completion_tokens` (integer, required): Number of output/completion tokens generated
- `model` (string, required): Model name (e.g. 'gpt-4o', 'claude-sonnet-4-6', 'gemini-2.0-flash')
- `prompt_tokens` (integer, required): Number of input/prompt tokens used
- `provider` (string, required): LLM provider
- `task_id` (string): Optional task identifier for grouping related calls

### `set_llm_budget` (~127 tokens)

Set a USD spend limit for an agent. The meter will return budget_status: 'warning' at the threshold and 'exceeded' when the limit is hit. Limits reset daily or monthly.

Input parameters:

- `agent_id` (string, required): Agent ID to set budget for
- `limit_usd` (number, required): Maximum USD spend allowed in the period (e.g. 10.00 for $10/day)
- `period` (string, required): Reset cadence
- `warning_threshold` (number): Fraction of limit that triggers 'warning' status (default: 0.8 = 80%)

### `get_spend_report` (~123 tokens)

Get LLM spend breakdown by agent, model, and provider. Filter by agent and date range. Returns total cost, call count, and per-model breakdown.

Input parameters:

- `agent_id` (string): Filter by agent ID (omit for all agents)
- `from_date` (string): ISO 8601 start date (e.g. '2026-04-01T00:00:00Z')
- `to_date` (string): ISO 8601 end date (e.g. '2026-04-30T23:59:59Z')

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 53
- 2026-07-31: 63
- 2026-07-29: 26
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/dingdawg-governance
- Socket report: https://socket.dev/npm/package/dingdawg-governance
- Repository: https://github.com/dingdawg/dingdawg-governance
- Changelog RSS feed: https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance/changelog.json
- HTML version of this page: https://verifymcp.io/servers/dingdawg-dingdawg-governance/dingdawg-governance