Xero Projects

Access Microsoft 365 emails, calendar, files, Teams, and people via Microsoft Graph. Six MCP servers with independent OAuth scopes — mail is split into read (user-consentable) and send (admin-consent).

9 MCP servers

Integrates Gmail, Drive, Calendar, Chat, and Contacts via Google Workspace MCP servers. OAuth 2.0 Bearer token auth — one token covers all five services.

2 agents · 5 MCP servers

Supplier bills from PDF to approved in each client’s own Xero organisation: read, checked and coded by AI, reviewed in WorkQ, with a weekly AP digest. Built for bookkeeping practices.

1 agent · 2 MCP servers

Client staff operations with Sprout: portal attendance and leave projections, monthly performance reviews, employee scorecards, and branded client reports. Includes portable custom tables and guided connector setup.

3 MCP servers

Lightweight SMB CRM backed by an Excel workbook. Stores contacts and accounts in Contacts and Accounts sheets and exposes CRUD operations over a stdio MCP server. Primarily used for testing the marketplace and plugin lifecycle.

1 agent · 1 MCP server

Manage Cliniko invoices, payments, and products via the myHub-hosted Cliniko MCP gateway. Invoicing, payment recording and allocation, products, and billable items.

1 MCP server

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Project Anatole: an optional, learning watchdog for unattended agents (OWASP-mapped rules, a per-project baseline, learn / notify / enforce modes). Default off.

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

Query Trackio projects, runs, and metrics using the `trackio` CLI. Use when the user needs to list projects/runs/metrics, get summaries, or retrieve metric values from local Trackio databases. Supports both human-readable and JSON output formats. Covers project discovery, run inspection, metric querying, and system metrics. Designed for LLM agents and automation scripts.

1 skill

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks