claude

Dregs

Dregs fraud and abuse detection integration. Investigate scored identities and their linked accounts, review and triage escalations, and tune badge and escalation rules against your own data. Connects over OAuth: run /mcp after installing.

1 on GitHubby Dregsv1.4.0MITupdated 20 days agosecurity
/

Plugin dregs from marketplace dregs in dregs-sdk/dregs-mcp. Commands read from the repo's manifest — 19 days ago.

What it installs

Skills (10)

  • connect

    Connect Claude Code to Dregs's MCP server and verify the connection. Use when Dregs tools are missing, a Dregs tool returns 401 or unauthorized, or the user asks to connect or reconnect Claude to Dregs. For integrating Dregs into the user's own application, use the setup skill instead.

  • health-check

    Diagnose the quality of a Dregs integration, read-only. Checks that events arrive, users are identified, event names and identity fields are mapped, analyzers produce observations, and the account is within its limits, then says what to fix. Use when scores look wrong or all sit in the middle, ident

  • investigate-cluster

    Map a ring of related accounts in Dregs starting from one identity: follow shared devices, IPs, sessions, and similar names or emails across hops, build the list of accounts with the evidence tying each in, and propose action. Use when the user suspects multi-accounting, referral fraud, registration

  • investigate-identity

    Investigate one identity in Dregs end to end. Read its scores and the observations behind them, its history, linked accounts, devices, and events, then reach a conclusion and take the right next step. Use when the user asks whether a user or account is legitimate, why an identity scored the way it d

  • setup-events

    Send server-side events to Dregs and map the user's event names and identity fields to Dregs's canonical types. Use when the user wants to track backend actions like payments or password resets, asks how to send events from their server, or when Dregs is receiving events but scores sit in the middle

  • setup-tracking

    Add the Dregs tracking script to the user's frontend, identify users at signup and login, and track key actions, then verify events arrive. Use when the user wants to install dregs.js, add the tracking snippet, call dregs.identify, or asks why Dregs shows no identities or only anonymous ones.

  • setup-webhooks

    Receive Dregs webhooks in the user's application, verify their signatures, and act on scores and escalations. Use when the user wants to build an endpoint for Dregs webhooks, verify the HMAC signature, react to score changes or escalations in their own system, or asks how to automate a response to f

  • setup

    Integrate Dregs into the user's application, end to end and under their supervision. Drives the setup-tracking, setup-events, and setup-webhooks skills in order, checking the account and confirming each step with the user. Use when the user wants to add Dregs to their app, integrate Dregs, install t

  • tune-rules

    Author or adjust Dregs badge rules and escalation rules against real data. Read the docs, inspect existing rules, preview the impact, and create or change rules only after confirmation. Use when the user wants to label identities (badges), get notified or open incidents on a pattern (escalations), r

  • weekly-review

    Produce a periodic health review of a Dregs account. Summarize scoring activity, the score distribution, which rules and badges fired, open escalations, and plan usage, then recommend what to look at or tune. Use when the user asks for a weekly or monthly review, a summary of what Dregs caught, a fr

MCP servers (1)

  • dregs

    connects to: https://dregs.com/mcp

View source on GitHub dregs.com

Similar plugins

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

anthropics/claude-code 155,476

Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.

12 skills

sickn33/agentic-awesome-skills 49,620

duende-skills

claudecodex

Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture

24 skills · 2 agents

anthropics/claude-plugins-official 47,076

SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening

5 skills · 3 commands · 2 agents

wshobson/agents 42,461

Maintain Dregs?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted