By Digitizers
Turns SUMIT (OfficeGuy) billing into agent-operable tools — customers, invoices, charges with an allow/charge cap, and document flows.
An MCP server that turns SUMIT (formerly OfficeGuy) into agent-operable Israeli billing — read invoices and debt, issue חשבונית/קבלה/חשבון עסקה, and charge with a confirm-first safety model. The operational playbook for billing your clients from Claude Code or OpenClaw.
sumit-api library (battle-tested payload builders + redaction).See .claude/skills/sumit-mcp/references/installation.md: clone, pnpm install && pnpm build, set SUMIT_* env, connect via claude mcp add or .mcp.json.
The committed .mcp.json holds env-var placeholders only and runs the committed dist/bundle.mjs, so it works both as the plugin's MCP config (${CLAUDE_PLUGIN_ROOT} set by the plugin cache) and straight from a clone — including claude.ai cloud sessions, where the SUMIT_* values come from the cloud environment's env vars. SUMIT_MAIN_COMPANY_ID/SUMIT_MAIN_API_KEY are deliberately bare ${VAR} placeholders: when they're unset, Claude Code rejects the config and never launches the server (fail closed) — the server process itself would boot with zero accounts and only error at tool-call time. Charging additionally stays behind its own env opt-ins (below).
Charging requires SUMIT_ALLOW_CHARGE=1, always goes prepare → user approval → execute, and needs a browser-minted one-time card token. See the skill's safety ladder. Set SUMIT_CONFIRM_SECRET to a fixed random value (e.g. openssl rand -hex 32); charging refuses to run without it.
The full threat model — what a misbehaving agent could try and which control stops it — is in SECURITY.md.
sumit-api, sumit-reactBuilt with ❤️ for OpenClaw by Digitizer
The plugin ships its skill through a git symlink (skills/ → the in-repo
source). On Windows, enable Developer Mode and set
git config --global core.symlinks true before cloning or installing —
the plugin cache clone inherits it. Changing the config does not repair an
existing checkout (the repo may have recorded core.symlinks=false locally).
To repair one, run these two commands inside it (the second re-materializes
only the plugin's symlink entry, so nothing else in your working tree is
touched):
git config core.symlinks true
git checkout -- skills/sumit-mcp
Or simply re-clone. WSL also works. macOS/Linux need nothing.
Admin access level
Server config contains admin-level keywords
Requires secrets
Needs API keys or credentials to function
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub digitizers/agent-skills --plugin sumit-mcpBuild WordPress sites with Claude Code via the Elementor MCP — native-widget-first building, Elementor 4 design system, brand kit intake, recipes, and error recovery.
Production-grade skill for managing Hostinger hosting via the official hostinger-api-mcp server — VPS, domains, DNS, backups, and safe write-gating.
Aura control-plane skill — drive approvals, snapshots, restores, and governed WordPress operations through the Aura/SiteAgent stack.
Operational guide for managing Cloudways servers and applications via the official Cloudways hosted MCP server — monitoring, analytics, Varnish, backups, cloning, staging, SSL, and safe write-gating.
Portable developer-workflow and design skills: canva-studio, codex-review-loop, fable-mode, figma-studio, gha-optimizer, magnific-studio, pr-first-workflow, safe-prod-db-write.
Browser automation and end-to-end testing MCP server by Microsoft. Enables Claude to interact with web pages, take screenshots, fill forms, click elements, and perform automated browser testing workflows.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.