Pax8 MCP

Pax8 + AI - for Claude, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the Pax8 API. Not affiliated with, endorsed by, or sponsored by Pax8, Inc.

[Pax8 demo - animated preview]

_{▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.}

Every Pax8 Partner API endpoint, plus an offline store that reconciles billing, tracks MRR, and catches usage overages no Pax8 tool surfaces. Works with the AI you already use - ChatGPT (desktop app), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Gemini CLI. Free, open source, runs on your laptop. Built for MSP owners. No code required.

Works with your agent

The six agents MSP owners actually use (self-serve, works today):

The ChatGPT desktop app runs pax8-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote server, which msp-skills does not support yet. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: Gemini CLI runs the local binary you just installed, while Microsoft 365 Copilot and the Gemini app need a remote server, which msp-skills does not support yet.

Skill-native agents (also covered): Hermes and OpenClaw read this skill's SKILL.md directly and speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: docs/which-agent.md.

Run more than one agent? Install across all 51+ supported agents in one command: npx skills add Servosity/msp-skills@latest (requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.

Install in 60 seconds

Fastest for Claude Desktop - one-click .mcpb

Claude Desktop bundle: the .mcpb launches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companion pax8-cli. Releases cut from 2026-09-18 on ship that CLI inside the bundle; older bundles contain only the MCP server, so if yours lacks the companion, run the Path A or Path B installer below first (or set PAX8_CLI_PATH to an existing binary). Details: #331.

Download Pax8 MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Pax8 release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills/plugin install pax8@msp-skills

Path A - paste one prompt into your AI agent (recommended)

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the Pax8 Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.ps1 | iex. Then authenticate per the README and run pax8-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.ps1 | iex

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.sh)

The installer drops both pax8-cli (the CLI) and pax8-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

pax8-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/pax8/install.ps1 | iex

Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update pax8@msp-skills.

Add to Claude Desktop, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, or another MCP client

After the installer runs, see mcp-install.md and docs/which-agent.md for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the ChatGPT desktop app. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.

Install for Hermes

From the Hermes CLI:

hermes skills install servosity/msp-skills/skills/pax8 --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/pax8 --force

Hermes speaks MCP natively, so it can also use the pax8-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the pax8 skill from https://github.com/servosity/msp-skills/tree/main/skills/pax8. The skill defines how its required CLI (pax8-cli) can be installed via the openclaw: frontmatter block.

OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.

Authenticate

Create an OAuth2 Client ID and Secret in the Pax8 portal under Integrations, then set the two credentials the CLI needs:

PAX8_CLIENT_ID=<value> PAX8_CLIENT_SECRET=<value> pax8-cli doctor

PAX8_AUDIENCE (default api://p8p.client) and PAX8_OAUTH_SCOPE are optional overrides for non-standard tenants. doctor confirms the credentials work before you run anything that touches data; pax8-cli auth login mints and caches the bearer token interactively. It exits 0 even when the credential is rejected, so scripts should add --fail-on error.

What this skill does

Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.

What makes this different

Most Pax8 integrations and MCP servers proxy each question into a live API call. That's fine for one record. It dies at scale, when you're asking where margin leaked across every customer last month, or which usage lines are about to overage before they invoice.

This skill syncs Pax8 into a local SQLite mirror with full-text search. Aggregate questions become one local SQL join: instant, offline, and the AI sees the answer, not the raw data. Compound commands like reconcile, mrr, and company show join across invoices, subscriptions, products, and usage - work a stateless API wrapper can't do.

The pain this closes

Pax8 is excellent at provisioning and ordering. It is not good at telling you, in one place, where the money is leaking. The marketplace hands you a monthly invoice file but never joins those lines back to your active subscriptions, so a line billing for a cancelled product - or a live subscription that never got invoiced - is yours to find by hand. Automation vendor Bumblebee profiled an MSP that spent five days every month reconciling Pax8 invoices against their PSA before automating it (hirebumblebee.com); Pax8's own developer docs are candid that mapping invoice lines back to subscriptions is real integration work (devx.pax8.com).

This skill closes that gap from the local mirror:

• pax8-cli reconcile - invoice lines with no active subscription, and active subscriptions never billed (--draft pre-checks the next unposted invoice)
• pax8-cli mrr - recurring revenue and margin by product, the spreadsheet you stop rebuilding
• pax8-cli overage - usage running hot before it posts to the customer invoice
• pax8-cli spend - customers ranked by total spend across invoices
• pax8-cli company show <companyId> - one customer's subscriptions, contacts, invoices, and usage in a single view

See pain-point.md for the longer narrative.

Frequently asked questions

Does this work with ChatGPT?

Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way pax8-mcp runs, and shares MCP configuration with Codex (OpenAI): add pax8-mcp under Settings > MCP servers as a STDIO server, or add it once to Codex's ~/.codex/config.toml. ChatGPT on the web is not supported by msp-skills yet: it needs a remote server. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list.

Does this work with Codex, Cursor, Windsurf, Cline, Copilot, or Gemini?

Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.

Do I need to know how to code?

No. The recommended install is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a one-line installer per OS (bash or PowerShell). Neither path requires writing code. You'll enter your Pax8 credentials once.

Is my Pax8 data safe?

Your data stays on your machine. The CLI and MCP server are local binaries. The SQLite mirror sits in a directory under your user account. The AI agent only sees what the CLI returns - typically a query result, not raw bulk data. Credentials are read from your environment or your agent's config; never bundled into this repo or transmitted anywhere by MSP Skills.

Do I need to be a Pax8 partner, and what credentials does it use?

Yes - it talks to the Pax8 Partner API with your own partner credentials. Create an OAuth2 Client ID and Client Secret in the Pax8 portal under Integrations, then set PAX8_CLIENT_ID and PAX8_CLIENT_SECRET. The CLI exchanges them for a bearer token at Pax8's token endpoint and caches it. PAX8_AUDIENCE (default api://p8p.client) and PAX8_OAUTH_SCOPE are optional overrides. The credential's own permissions are the real boundary - scope it to what you want the AI to reach.

Will this hit my Pax8 API rate limits?

After the first sync, the analytics commands (reconcile, mrr, overage, spend, since, company show, search) run against your local SQLite mirror with zero API calls. Live calls respect a --rate-limit throttle. No Pax8 list endpoint has a changed-since filter, so each sync re-reads your companies and subscriptions (and the other resources it mirrors). The since command then reports stored subscription history plus current subscriptions created or updated within the window you choose.

Does this replace the Pax8 portal?

No. Provisioning, ordering, and support workflows stay in the portal. This skill answers the cross-entity billing and revenue questions the portal cannot compose in one place - reconciliation, MRR and margin, usage overages, customer-360 - from your terminal or agent.

What does it cost?

Free. Apache-2.0 licensed. You pay only for whichever AI agent you use (Claude, ChatGPT, Codex, etc.), and that's billed by your AI provider, not by us.

Safety model

The strongest control is the scope you grant the Pax8 credentials - the CLI can only do what the credentials are permitted to do. Full details, including how to lock it down, are in governance.md.

Status

Beta. Validated against the Pax8 API surface and being validated with MSPs running it live against their own production tenant in our weekly Build Sessions. RSVP at compoundingteams.com/build-sessions.

Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes. OpenClaw-ready (frontmatter pre-wired, awaiting OpenClaw launch).

Maintained by Servosity. Apache-2.0 licensed. Built with CLI Printing Press. Last updated: 2026-06-05.