mcpField
D
dingdawg-loop

dingdawg-loop

Local
github.com/dingdawgAI & Agents0Updated 15w ago
Repository

About dingdawg-loop

dingdawg-loop is an MCP server that places governance gates around scheduled AI agent actions. It is for teams that need risk checks, signed receipts, and audit history for recurring tasks.

Key features

  1. 01Register scheduled loops and policies
  2. 02Evaluate actions before execution
  3. 03Gate high-risk operations
  4. 04Sign execution receipts with Ed25519
  5. 05Pause and resume loops
  6. 06Retrieve per-loop audit history

Use cases

  1. 01Require approval thresholds for sensitive tasks
  2. 02Prevent unapproved financial or destructive actions
  3. 03Pause a recurring agent workflow
  4. 04Review signed execution records

MCP support

Provides MCP tools to register, execute, list, pause, resume, and audit scheduled loops. It works with MCP-compatible clients and can connect through MCP bridges for CrewAI and LangGraph.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dingdawg-dingdawg-loop": {
      "command": "npx",
      "args": [
        "-y",
        "dingdawg-loop"
      ],
      "env": {
        "DINGDAWG_API_KEY": "<DINGDAWG_API_KEY>"
      }
    }
  }
}
Run commandnpx -y dingdawg-loop
Environment variables to set
DINGDAWG_API_KEYSecretAPI key for paid tier access — get free at dingdawg.com

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmdingdawg-loop2.0.8

Tools

6

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
namestringYesHuman-readable name for this loop (e.g., 'daily-report-sender', 'hourly-health-check')
metadataobjectNoOptional key-value metadata (e.g., owner, team, target_system)
schedulestringYesCron expression for the schedule (e.g., '0 9 * * *' for daily at 9am, '@hourly'). Stored but not auto-executed in v1.
risk_tierenumYesRisk tier — determines governance gate strictness. 'critical' loops will almost always require human review.low | medium | high | critical
action_typestringYesType of action this loop performs (e.g., 'send_email', 'generate_report', 'sync_data', 'health_check')
descriptionstringYesDetailed description of what this loop does each cycle. Be specific — governance evaluates this text.

Details

From the project README

dingdawg-loop

DingDawg Loop Protocol (DDLP) — safe scheduled AI agents with governance gates.

Every loop execution is verified, receipted, and fail-closed. MCP-native. Works with CrewAI, LangGraph, Claude Code, and Cursor.

Install

npx dingdawg-loop

Or as an MCP server in Claude Desktop / Claude Code:

{
  "mcpServers": {
    "dingdawg-loop": {
      "command": "npx",
      "args": ["dingdawg-loop"]
    }
  }
}

What it does

DDLP wraps any scheduled agent action with a governance gate that:

  • Evaluates the loop description before execution
  • Blocks destructive, financial, or sensitive operations until policy thresholds are met
  • Signs every execution with an Ed25519 receipt
  • Provides full audit history per loop

MCP Tools

ToolDescription
register_loopRegister a new scheduled loop with name, description, cron, and governance policy
execute_loopRun one cycle of a registered loop — governance gate fires before any action
list_loopsList all registered loops with status, last execution, and receipt count
pause_loopPause a running loop — no executions until resumed
resume_loopResume a paused loop
loop_auditRetrieve the full signed receipt audit trail for any loop

Governance gates

DDLP classifies every loop at registration time. High-risk categories require elevated approval:

  • Destructive operations — file deletion, database mutations, DROP statements
  • External communications — email sends, Slack messages, webhook calls
  • Financial operations — any spend, transfer, or payment action
  • Sensitive data access — PII reads, credential access, health records
  • Bulk operations — mass updates, batch sends, bulk deletes

Compatibility

Works with any MCP-compatible AI client:

  • Claude Desktop / Claude Code
  • Cursor
  • CrewAI (via MCP bridge)
  • LangGraph (via MCP bridge)

License

BUSL-1.1 — see LICENSE

Publisher

DingDawg Enterprise — [email protected] — dingdawg.com

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.