Xnurta MCP connects advertising data from the Xnurta platform to the AI assistant you already use. After setup, you can use natural language to query ad performance, entity configuration, and operation logs. You can also ask AI to combine Xnurta data with your own cost, margin, targets, or other business context for analysis.

The current version supports data queries, AI managed-group management, ad-entity editing, and Sponsored Products campaign creation. Write operations require the corresponding permission and explicit confirmation where required.

MCP, or Model Context Protocol, is a standard protocol that allows AI assistants to connect to external systems. You can think of it as a standard way for AI assistants to access business systems.

Compared with an API, an API is usually designed for systems or developers. To integrate a system through APIs, engineers often need to read API documentation, write code, handle authentication, and map fields. MCP builds on top of API capabilities and provides a more standardized connection method for AI assistants.

Xnurta packages platform data access capabilities as MCP Tools, and AI assistants call these Tools through the MCP protocol. This means you do not need to write code or remember every API and field name. You can ask questions in natural language and let AI query and analyze the data.

In one sentence:

MCP is the USB-C of the AI world. We turn Xnurta advertising capabilities into a standard connector, so your AI can plug in and use them.

After setup, you can use Xnurta MCP in an AI assistant that supports MCP to:

Xnurta MCP currently supports three query-data categories, AI managed-group management, ad-entity editing, and Sponsored Products campaign creation.

This includes advertising performance metrics and selected business metrics, such as:

This includes key advertising objects and configuration in the ad account, such as:

This includes operation records from both users and AI, such as:

This includes AI managed group create, edit and delete:

Before using Xnurta MCP, make sure you have:

Start querying in natural language.

Choose the setup path that matches your AI client. Xnurta MCP supports OAuth and MCP Token authorization.

You can manage manually created MCP Tokens from the MCP Token management page in Xnurta.

Use this path for Claude Code, Codex, and other AI clients that can configure an MCP server from a prompt. You do not need to create, copy, or store an MCP Token.

When your AI client prompts you to authenticate, continue in the browser:

The AI client normally installs the Skills while configuring MCP. If MCP is connected but the Skills were not installed, send the following prompt:

Claude Cowork, the Claude desktop app, and claude.ai connect to Xnurta through a Custom Connector. Do not use the setup prompt in Option A or manually configure an MCP Token for these clients.

Free / Pro / Max: add the connector yourself.

Team / Enterprise: an Owner or Primary Owner adds the connector once for the organization, and each member then connects it individually.

Sign in to Xnurta in the browser window, review the requested permissions and Profiles, approve the authorization, and return to Claude. Each member authorizes with their own Xnurta account, so an organization-level connector does not expand anyone's store access or permissions.

The connector and Skills are separate. Adding the connector completes MCP authorization but does not install Skills. In a new chat, ask Claude to install or update the Xnurta Skills from the repository:

Step-by-step guide:

Use this path only for AI clients that support manual MCP Token configuration. Claude Cowork, the Claude desktop app, and claude.ai must use the Custom Connector in Option B.

Note: You usually cannot view the Token again after leaving the page. If you did not save it, create a new one.

We recommend using the one-prompt setup method. Open an AI assistant that supports MCP and send the following prompt:

The AI assistant will configure MCP based on the repository instructions and call the verification tool. If it returns your user information and authorized store or Profile list, the setup is successful.

If your AI assistant does not support automatic setup, add a remote MCP service in the client's MCP settings.

MCP service URL:

Request header:

Claude Code CLI example:

ChatGPT Codex example:

Different AI assistants may have different MCP settings. If you see a 401 error, the Token may be incorrect or missing permission. If the request times out, check your network connection and MCP configuration.

Existing connections do not automatically receive newly added write scopes. Customers who already use Xnurta MCP must re-authorize the connection and update their Skills before using ad-entity editing or SP campaign creation.

Campaign creation does not require a separate application for main accounts that already have campaign-editing access, but re-authorization and a Skills update are still required.

After setup, you can ask questions in natural language. For more accurate results, include:

Common question scenarios include:

Use this for daily account checks or weekly performance reviews.

Use this to diagnose a specific campaign, product, or product line.

Use this to find wasted spend, promising search terms, or targeting that needs adjustment.

Use this to check whether ad budget and traffic allocation are reasonable.

Use this to understand whether performance changes are related to human or AI operations.

If you have your own cost, margin, inventory, or target data, provide it in the conversation and ask AI to analyze it together with Xnurta data.

If you need the same analysis framework on a regular basis, use a Skill or a fixed prompt.

A Skill is a reusable set of analysis instructions. After a Skill is installed, the AI assistant follows fixed steps to query data, analyze it, and produce output for the matching scenario.

Common official Skills include:

In most cases, when you configure Xnurta MCP by following the GitHub repository instructions, the AI assistant will install the required official Skills for you. After setup, you can ask the AI assistant to confirm the list of installed Skills.

If the AI assistant does not install them automatically, or if your client requires manual installation, tell the AI assistant which Skill you want to use. For example:

Or:

The AI assistant will guide you through the installation. After installation, you can say "Generate last week's advertising report" or "Help me run a product diagnosis." If the AI assistant asks you to upload or select a Skill file, follow the instructions in your client.

If your team has a fixed analysis method, you can turn it into a custom Skill. We recommend defining:

Output format: table, summary, action item list

Note:

Managed group management will actually modify your account configuration. We recommend asking the AI to first show the objects, target ACOS, AI status, action space, and campaign list it plans to change, then confirming before it executes.

The assistant shows the affected objects and the old and new values before operations involving money, bids, or archiving are submitted.

SP campaign creation is atomic: if any campaign in the request fails validation, none are created. Create campaigns as paused when you want to review them before they spend. SB and SD campaign creation are not currently supported.

Within the scope authorized by the customer, Xnurta MCP enables MCP-compatible AI clients such as Claude, Codex, and Cursor to query Xnurta data. The following sections explain how Xnurta MCP accesses and processes that data.

Connecting Xnurta MCP does not give an AI client access to the entire Xnurta account. Every request is subject to Xnurta identity and permission checks. The accessible scope is determined by the intersection of the current user's permissions, the MCP Token permissions, and the authorized Profiles. An MCP Token cannot expand the user's existing data permissions.

Xnurta MCP can provide data retrieval and advertising management capabilities, depending on the tools currently available and the permissions granted to the MCP Token. Read and write permissions are controlled separately. Without the relevant write permission, MCP cannot modify an advertising account. For a request that may change a Campaign, Budget, Bid, or other configuration, the client must display the proposed action and execute it only after receiving explicit confirmation from the user.

The AI client sends the parameters and call information required for a request to Xnurta only when it invokes an Xnurta MCP tool. After completing the permission checks, Xnurta performs the authorized data query or advertising action and returns the result to the client. Connecting MCP does not initiate a full data sync or automatically perform advertising actions. Xnurta also does not automatically receive the user's entire conversation with the AI client simply because MCP is connected.

After a tool result is returned to the AI client, the customer's selected AI client and model provider continue processing it. Whether the provider stores the data, how long it retains the data, and whether it uses the data for product improvement or model training depend on the provider's product tier, contract, privacy policy, and account settings. Xnurta does not control these third-party practices.

Enterprise customers should use AI services and enterprise accounts approved by their internal security and legal teams. They should also configure data retention, model improvement, and data-sharing settings according to their own data governance requirements.

An MCP Token identifies the user and authorizes access. Manage it with the same level of security as a password or API Key. Do not include a Token in a chat, document, or support ticket, and do not share a personal Token with other people. If a Token is exposed or no longer needed, disable or delete it in Xnurta immediately.

First, ask AI to call get_user_authorized_context to verify authorization. If it cannot return authorized stores or profiles, check whether the Token is correct, expired, or missing the required store or ad account permission.

MCP provides queryable data. The final analysis is generated by the AI assistant. Different AI assistants, conversation context, and question wording may change how conclusions are organized. To improve consistency, specify the time range, object, metrics, and output format in your question.

Use InsightAgent when you want ready-made analysis directly inside the Xnurta platform. InsightAgent is better for out-of-the-box ad diagnosis, anomaly analysis, and platform-based reviews.

Use MCP when you want to query Xnurta data in your own AI assistant, or when you need to combine it with your own cost, margin, inventory, targets, internal spreadsheets, or other context. MCP is better for follow-up questions, cross-source analysis, fixed report generation, and personalized workflows.

They are not replacements for each other. InsightAgent helps you get standard conclusions quickly inside the platform. MCP brings Xnurta data into your own AI workflow for further analysis.

Platform reports are better for fixed dashboards and standard metrics. MCP is better for natural-language queries, cross-source analysis, fixed report generation, and personalized follow-up questions in your own AI assistant. You can use both together.

You usually do not need to remember every field name. Natural-language descriptions are enough for daily use. The following reference is only for cases where you need to specify metrics or objects precisely.

Purpose: create, edit, schedule, and delete managed groups via natural language — single or in bulk.

Create / Edit (same settable items; grouped by the edit page’s sections)

Bulk supported (multiple groups at once); some changes may be skipped while AI is running.

Delete

Platform UI only (not writable via MCP)

Purpose: bulk-edit the ads themselves through natural language.

Campaign

Product

Target — auto targeting, keywords, product targeting

Negative targets — negative keywords, negative products

Confirmation before execution

Operations involving money, bids, or archiving are never executed straight away — the assistant returns a preview first (which objects, and from what value to what value), and submits only after you confirm.

Purpose: create one or more SP campaigns through natural language.

SB and SD campaign creation are not supported. A campaign cannot be deleted after creation; it can only be archived, which is irreversible.