> For the complete documentation index, see [llms.txt](https://playbook.nativemsg.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://playbook.nativemsg.com/mcp/overview.md).

# nativeMsg MCP Server

Connect your AI tools directly to nativeMsg. The MCP server lets any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, and others — build, send, and manage branded RCS experiences in plain language, using your nativeMsg account.

**Server URL:** `https://mcp.nativemsg.com/mcp` **Transport:** Streamable HTTP · **Auth:** OAuth 2.1 (sign in with your nativeMsg login)

## What your agent can do

* **Build complete RCS experiences** — storefronts, booking flows, lead-gen campaigns, order trackers — as conversations with branching, data capture, and live connections to your own systems. Every change is saved as a revision you can roll back. → [Experiences tools](/mcp/tool-reference/experiences.md), [Build an experience](/mcp/guides/build-an-experience.md)
* **Send rich, branded RCS** — text, media, rich cards, carousels, buttons, quick replies, and lists, from your carrier-verified brand, with automatic SMS fallback. → [Messaging tools](/mcp/tool-reference/messaging.md)
* **Run campaigns** — create blasts, target by tag, count recipients before sending, schedule, cancel, and track delivery. → [Blasts tools](/mcp/tool-reference/blasts.md), [Run a campaign](/mcp/guides/run-a-campaign.md)
* **Manage the account** — channels, contacts, tags, templates, webhooks, and RCS capability checks. → [Tool reference](#tool-reference)

## Get connected

Two minutes, no API keys: copy the server URL, add it to your AI tool, sign in. Step-by-step for each client in the [Quickstart](/mcp/quickstart.md).

## Tool reference

73 tools, grouped by what they work on:

| Group                   | Tools | Reference                                                 |
| ----------------------- | ----- | --------------------------------------------------------- |
| Experiences & revisions | 10    | [Experiences](/mcp/tool-reference/experiences.md)         |
| Channels                | 9     | [Channels](/mcp/tool-reference/channels.md)               |
| Contacts & tags         | 18    | [Contacts & Tags](/mcp/tool-reference/contacts.md)        |
| Messaging & templates   | 15    | [Messaging & Templates](/mcp/tool-reference/messaging.md) |
| Blasts                  | 13    | [Blasts](/mcp/tool-reference/blasts.md)                   |
| Webhooks                | 5     | [Webhooks](/mcp/tool-reference/webhooks.md)               |

Plus 2 deprecated aliases (`list_bots`, `get_bot`) — see [Versioning & deprecations](/mcp/versioning.md).

## Built-in safeguards

Real messages, real guardrails: OAuth-scoped access you can revoke anytime, destructive-operation annotations your AI client uses to ask before acting, refuse-unless-forced protection on anything live (subscribed contacts, scheduled blasts), recipient counts before every send, and revision history on every experience change. Details in [Safety & approvals](/mcp/guides/safety-and-approvals.md).

## More

* [Authentication & scopes](/mcp/authentication.md)
* [Troubleshooting](/mcp/troubleshooting.md)
* [Versioning & deprecations](/mcp/versioning.md)
* RCS Experience Schema reference: [playbook.nativemsg.com/rcs-experience-schema](https://playbook.nativemsg.com/rcs-experience-schema)
* REST API (for wiring nativeMsg into your own systems): [docs.nativemsg.com](https://docs.nativemsg.com)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://playbook.nativemsg.com/mcp/overview.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.