Dingdawg Loop

io.github.dingdawgPublished by GitHub account dingdawgv2.0.8Updated Oct 25, 2026

Safe scheduled AI agents with governance gates. Verified, receipted, fail-closed.

Overview

AI-generated overview

A local MCP server that registers scheduled AI agent loops and runs each cycle through a governance gate with signed audit receipts.

What you can do
Register scheduled loops with a name, description, cron schedule and governance policy, and list them with status, last run and receipt counts. Run one cycle of a registered loop, with the governance gate firing before any action. Pause and resume loops so no executions happen until resumed. Retrieve the full signed receipt audit trail for any loop. Classify loops by risk at registration, holding back destructive, financial, external-communication, sensitive-data and bulk operations until policy thresholds are met.
When to use it
Useful when you want an assistant to schedule recurring agent actions but need a gate that blocks high-risk operations and keeps a verifiable audit trail. Fits teams already running agents in Claude Desktop, Claude Code, Cursor, CrewAI or LangGraph that need per-loop governance and receipts.
Requirements
Runs as a local process on the user's machine, started with npx from the npm package dingdawg-loop, so Node.js and network access for the package are needed. Desktop client only. An API key in the environment variable DINGDAWG_API_KEY is used for paid tier access; a free key is offered by the publisher.
Before you install
The server asks for DINGDAWG_API_KEY, a secret that should be supplied through the environment and not shared. Loops can perform destructive, financial, external-communication, sensitive-data and bulk operations once thresholds are met, so review each loop's governance policy before running it. Executions are signed and audited, which means loop activity and receipts are recorded.

Installation

In SourceWeft

  1. Open Dingdawg Loop in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

bash
npx dingdawg-loop

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

json
{  "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

Source: README.md at commit c1c19f9

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v2.0.8LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts