> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tagada.io/llms.txt
> Use this file to discover all available pages before exploring further.

# CRM MCP Server

> Read-only Model Context Protocol server for your TagadaPay account — let AI agents diagnose your store, processors, webhooks, and domains

# CRM MCP Server

The **TagadaPay CRM MCP Server** (`@tagadapay/crm-mcp`) is a [Model Context Protocol](https://modelcontextprotocol.io) server that exposes a **read-only view of your TagadaPay account** to any MCP-compatible AI agent — Claude, Cursor, Windsurf, ChatGPT desktop, or your own.

It is the same diagnostic surface that powers the in-app **Auto-fix agent** (the chat widget on `app.tagadapay.com`) and the Crisp support agent. Now you can plug it into your own AI tooling.

<Note>
  **Read-only by design.** This MCP can answer "how is my account configured?" but it cannot change anything. Mutations always go through the in-app approval flow so a merchant explicitly clicks "Apply" before any change lands. See [How writes are gated](#how-writes-are-gated) below.
</Note>

## How it works

```
AI Agent  →  CRM MCP Server (local)  →  HTTPS + API key  →  api.tagada.io
                                                                   ↓
                                                       processors, stores,
                                                       webhooks, domains, …
```

<Steps>
  <Step title="Get an API key">
    From the dashboard: **Settings → API Keys → Create**. Scope it to `read`.
  </Step>

  <Step title="Add the MCP server to your AI tool">
    One JSON snippet in `.cursor/mcp.json` (or your tool's equivalent). See [Quick Start](/developer-tools/crm-mcp/quick-start).
  </Step>

  <Step title="Ask the agent">
    "Why are my payments declining?" → the agent inspects processors, webhook deliveries, domains, and answers with real data from your account.
  </Step>
</Steps>

## What can agents read?

Thirteen tools at v1, all read-only, all backed by the [Node SDK](/developer-tools/node-sdk/quick-start):

| Tool                   | Returns                                            |
| ---------------------- | -------------------------------------------------- |
| `orders.list`          | Orders with filters and pagination                 |
| `orders.retrieve`      | A single order by id                               |
| `stores.list`          | Stores on the account                              |
| `stores.retrieve`      | A single store by id                               |
| `processors.list`      | Payment processors (active, currencies, countries) |
| `processors.retrieve`  | A single processor by id                           |
| `funnels.list`         | Funnels for a store                                |
| `funnels.retrieve`     | A funnel's full config                             |
| `customers.list`       | Customers with optional email filter               |
| `customers.retrieve`   | A single customer by id                            |
| `webhooks.list`        | Webhook endpoints on a store                       |
| `domains.list`         | Custom domains with verification status            |
| `domains.getDnsLookup` | Live DNS lookup, runs from TagadaPay infra         |

See [Tools Reference](/developer-tools/crm-mcp/tools-reference) for full schemas.

## What agents *can't* do via this MCP

* **Mutate anything.** No "enable processor", no "add webhook", no "promote funnel". This MCP has zero write tools.
* **Cross-account access.** The API key is scoped to one account. Any tool call is implicitly filtered by `accountId`.
* **Read PII or card data.** Customer emails, card PANs, and payment instrument tokens are out of scope. Only configuration data is exposed.

## How writes are gated

If you want an AI agent to actually *fix* a misconfiguration (e.g., re-enable a disabled processor), use the in-app **Auto-fix agent** instead. That agent runs server-side, proposes a plan, and the merchant approves it inline in the dashboard widget — every change is HMAC-signed, plan-hash-locked, and audited.

The CRM MCP is the **diagnostic layer**. It tells you *what* is wrong; the in-app agent gives you the one-click fix.

This separation is intentional: a misbehaving external AI agent (prompt-injected, jail-broken, whatever) can at worst make a redundant `read_*` call. It can never push a button on your account.

## Pairs well with

| Surface                                                | What it does                                         |
| ------------------------------------------------------ | ---------------------------------------------------- |
| [Studio MCP](/developer-tools/studio-mcp/introduction) | Live edit Studio templates from an AI agent          |
| [Node SDK](/developer-tools/node-sdk/quick-start)      | Server-side write access to the full TagadaPay API   |
| In-app Auto-fix agent                                  | Approval-gated mutations, available in the dashboard |

## Next steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/developer-tools/crm-mcp/quick-start">
    Get an API key and connect Cursor or Claude in 2 minutes
  </Card>

  <Card title="Tools Reference" icon="wrench" href="/developer-tools/crm-mcp/tools-reference">
    Every tool with input/output schemas
  </Card>

  <Card title="Examples" icon="lightbulb" href="/developer-tools/crm-mcp/examples">
    Sample prompts for diagnosing common issues
  </Card>

  <Card title="Studio MCP" icon="pen-paintbrush" href="/developer-tools/studio-mcp/introduction">
    Edit your Studio templates live with an AI agent
  </Card>
</CardGroup>