Dingdawg Support Agent
- 1 repo stars
- Updated July 7, 2026
- dingdawg/dingdawg-agent-1
Dingdawg Support Agent is an MCP server that classifies support tickets, drafts replies, and routes escalations through Dingdawg from your AI agent.
About
Dingdawg Support Agent is an MCP server that connects AI coding agents to Dingdawg’s support automation: ticket classification, response drafting, and escalation routing. Developers running a small SaaS or product with real user email can register the stdio server in Claude Code, Cursor, or similar hosts so support triage happens alongside development work. You need a Dingdawg API key for paid access; a free tier is advertised on dingdawg.com. The integration is purpose-built for communication workflows, not for building features or running infrastructure. It fits when ticket volume is low enough that a full helpdesk team is unrealistic but replies still need consistency and faster first responses. Expect agent-mediated suggestions you review before sending—appropriate for developers who want leverage without handing the inbox fully to an unattended bot.
- Classifies inbound support tickets via MCP from your agent
- Drafts customer-facing response text for review or send
- Routes or flags tickets that need human escalation
- Stdio npm package dingdawg-support-agent v2.0.6
- Paid tier uses DINGDAWG_API_KEY (free tier signup at dingdawg.com)
Dingdawg Support Agent by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env DINGDAWG_API_KEY=YOUR_DINGDAWG_API_KEY dingdawg-support-agent -- npx -y dingdawg-support-agentAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 1 |
|---|---|
| Package | dingdawg-support-agent |
| Transport | STDIO |
| Auth | Required |
| Last updated | July 7, 2026 |
| Repository | dingdawg/dingdawg-agent-1 ↗ |
What it does
Wire your coding agent into Dingdawg so inbound tickets get classified, draft replies suggested, and escalations routed without leaving the IDE.
Who is it for?
Best when you handle support in Claude Code or Cursor and want Dingdawg-backed classification and reply drafts on a free or paid API tier.
Skip if: Skip if you need a full standalone helpdesk UI with no MCP host, or developers with zero Dingdawg account and no interest in a third-party support API.
What you get
After you add the stdio server and API key, your agent can propose classifications, draft responses, and escalation paths so you approve and send faster.
- Ticket classification suggestions from Dingdawg tools
- Draft support responses for builder review
- Escalation routing recommendations on inbound tickets
By the numbers
- Server schema version 2.0.6
- Transport: stdio via npm identifier dingdawg-support-agent
- One required secret env var: DINGDAWG_API_KEY
README.md
ISG Agent 1
Governance from Day 1. A security-hardened, governance-first autonomous AI agent platform.
ISG Agent 1 proves that autonomous AI agents can be both powerful and safe. While other agent platforms bolt on security as an afterthought, ISG Agent 1 bakes governance into every layer from the start.
7 Innovations No Other Agent Has
| Innovation | What It Does |
|---|---|
| Agent Constitution | Machine-enforced behavioral contract -- not guidelines, a verified contract |
| Adversarial Self-Testing | The agent red-teams itself in production on a schedule |
| Time-Locked Actions | Mandatory cooling period before dangerous operations (30-60s) |
| Trust Ledger | Transparent, cryptographic reputation tracking for every action |
| Explain Mode | Cryptographic proof of why every decision was made |
| Skill Reputation | Community-verified trust scores for agent skills |
| Separation of Powers | Critical actions require approval from independent agent or human |
Security Comparison
ISG Agent 1 was built as a direct response to the security failures in existing agent platforms. Where others have exposed instances, malicious skills, and no audit trails, ISG Agent 1 has localhost-only defaults, skill quarantine, and hash-chained audit logs.
Quickstart
git clone https://github.com/InnovativeSystemsGlobal/isg-agent-1.git
cd isg-agent-1
cd gateway
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp ../.env.example ../.env
cp ../config/agent.example.yaml ../config/agent.yaml
python -m isg_agent
The gateway starts on http://localhost:8900 by default (localhost-only).
Architecture
User (Discord/Telegram/Web)
-> Bridge (TypeScript, normalizes messages)
-> Gateway (Python/FastAPI, governance engine)
-> Constitution check
-> Governance gate (PROCEED/REVIEW/HALT)
-> Audit trail (SHA-256 hash chain)
-> Brain (LLM + convergence guarantees)
-> Skills (sandboxed, quarantined, reputation-scored)
-> Response (governed, explained, audited)
See ARCHITECTURE.md for the full architecture overview.
Documentation
- Quickstart Guide
- Architecture Overview
- Security Model
- The 7 Innovations
- Constitution Guide
- Skill Development
- Deployment Guide
- API Reference
Contributing
See CONTRIBUTING.md for contribution guidelines.
Security
See SECURITY.md for our responsible disclosure policy.
License
MIT License. See LICENSE for details.
Innovative Systems Global. The name is not aspirational. It is a statement of fact.
Recommended MCP Servers
A2atlassianJira & Confluence for AI agents.
Abm McpAccount-based marketing for AI agents.1
ACA Automated Client AcquisitionGenerate on-brand content, manage leads, and run outreach across 6 channels from your AI agent.
Activitypub McpRead-only-by-default MCP server: let LLMs explore the Fediverse — Mastodon, Misskey, Pleroma.17
Adaptive Cards McpGenerate, validate, and optimize Adaptive Cards for Teams, Outlook, and Copilot.31Adbloop Meta AdsSafe bulk Meta ads: launch 150+ campaigns from Drive folders with spend guardrails and validation.How it compares
MCP integration to a hosted support agent API, not a local skill that rewrites your codebase.
FAQ
Who is Dingdawg Support Agent for?
and small-team developers who run user-facing products and want their coding agent to help triage and draft support tickets via Dingdawg.
When should I use Dingdawg Support Agent?
Use it in the Grow support phase when you have recurring tickets and want classification, draft replies, and escalation routing without opening a separate toolchain for every message.
How do I add Dingdawg Support Agent to my agent?
Register the npm stdio server dingdawg-support-agent in your MCP client, set the secret DINGDAWG_API_KEY environment variable, and restart the host so tools can call Dingdawg.