# The PYLO plugin for Claude

Install PYLO into Claude Code and run onboarding, weekly reviews and integration fixes from a conversation.

## What it is

The PYLO plugin connects Claude to your workspace through PYLO's MCP server and adds three skills: step by step playbooks Claude follows when you ask for the job they cover. Claude reads your figures, proposes changes as plans a person approves, and never sees a credential.

The plugin comes in two versions with the same skills and the same tools:

| Plugin | Signs in with | Use it when |
|---|---|---|
| pylo | An API token from Settings, API tokens | Today. This is the one to install. |
| pylo-oauth | Your PYLO account, through a consent screen | Once PYLO's sign-in for Claude is live on your deployment. It is off by default. |

Install one of the two, not both. They expose the same tools.

## Install

You need Claude Code and a PYLO token. A workspace token from [API tokens](/docs/settings/api-tokens) is read only, which is enough for weekly reviews and for diagnosing an integration. Planning and applying changes, sending connect links and running test leads need an agency token from [Agency settings](/docs/agency/settings), issued with those permissions. Agency tokens, and every plan, apply and undo, need the [Pro plan](/docs/billing-and-plans). Either is shown once, so copy it straight into Claude Code when asked.

In Claude Code, add PYLO's plugin marketplace, which is the public repository [chigozieumeukeje19-netizen/pylo-claude-plugin](https://github.com/chigozieumeukeje19-netizen/pylo-claude-plugin), then install the plugin:

```
/plugin marketplace add chigozieumeukeje19-netizen/pylo-claude-plugin
/plugin install pylo@pylo
```

Claude Code then asks for two settings:

| Setting | What to enter |
|---|---|
| PYLO API token | The token you just issued. Claude Code keeps it in your system keychain. It never goes in a file or into the conversation. |
| PYLO MCP URL | Leave the default, https://api.pylosystem.com/mcp, unless PYLO has told you otherwise. |

To sign in with your PYLO account instead, install the second plugin. It asks only for the MCP URL, then opens PYLO's consent screen on first use, where you choose what Claude may do. PYLO caps what you grant to what your role already allows.

**Belong to more than one workspace?** The consent screen lists every workspace you are an active member of. Tick the ones Claude may use. It works in one at a time, with your role in that workspace, starting in the one you have open. Ask it to move ("switch to Northside") and it uses `switch_workspace` and tells you where it is now. A workspace you leave drops out on the next switch. If you are in an agency you can instead sign it in for the whole agency, which reaches every client workspace in it.

```
/plugin install pylo-oauth@pylo
```

## Just the tools, without the skills

If you only want Claude to read PYLO, add the MCP server on its own:

```
claude mcp add --transport http pylo https://api.pylosystem.com/mcp --header "Authorization: Bearer YOUR-TOKEN"
```

Every tool it offers is listed in the [MCP reference](/docs/mcp).

## The skills

### weekly-review

Ask for a weekly review, a health check, or where a client's funnel is leaking. Claude changes nothing. It first asks PYLO whether the week's figures can be trusted, then finds the one stage losing the most, proves it from PYLO's own figures, and proposes at most two actions.

It follows fixed rules. Every figure comes from PYLO and is never estimated. Every rate is stated with both sides, for example a show rate as live calls out of live calls plus no-shows. A figure PYLO cannot compute is reported with its reason, never as zero. Money keeps the currency PYLO returned.

### fix-integration

Ask why a tool stopped syncing, why data is missing, or why notifications stopped. Claude reads your [connector health](/docs/settings/integrations) and the data trust checks, works out why a provider is quiet or failing, and proposes the fix as a plan for a person to approve or a connect link for the client to complete.

It never asks for an API key, token, webhook address or password. If one is pasted into the conversation, it tells you to revoke it. It only calls something fixed once PYLO reads it back as working.

### onboard-client

Tell Claude you signed a client. It runs the whole onboarding from the conversation, through your 7-day checklist: it drafts the workspace from a template and the client's intake, shows each plan and waits for a person's approval, sends the client one link for their tools and keys, chooses and builds the stack, drafts the copy for you to approve, times the reminders, adds the sales team, and runs the backend test and a test lead. After every step it asks PYLO for the one next thing, so a new conversation carries on where the last one stopped, and it tells you when the run is waiting on you or the client. See [Onboarding](/docs/agency/onboarding).

Planning a brand new workspace needs an agency token. An owner signed in through pylo-oauth works on their own workspace.

## What Claude can and cannot do

Claude can read anything the token or your sign-in allows, on either plan. On Pro it can also plan and apply configuration once a person approves. It cannot move money, refund, pay out, edit a payment or delete anything: PYLO has no tool for any of those. Changes are always shown as a plan first and applied only with a person's approval.