MOBIDI MCP for AI. Query Ad Data & Manage Campaigns Via AI Agent

Q: How do I check if the MOBIDI MCP Server can actually connect?

Run checkmobidistatus. This tool verifies your API connectivity right away. It's a simple, necessary step before running any other command to make sure data gets through.

Q: What if I need to query records but don't know the entity type?

Run listentitytypes first. This gives you an exhaustive list of all available data structures (like 'Customer', 'Order', etc.), so you can correctly target your query with listrecords.

Q: How do I run a pre-built sales report using the MOBIDI MCP Server?

First, use listreports to get the exact name of the report. Then, pass that name into the executereport tool. The agent returns the structured data directly.

Q: Can I update a record without knowing its ID?

No, you need an ID for updates. You must first use listrecords to query and find the specific records matching your criteria, then select the target ID before calling updaterecord.

Q: How do I find out what platform capabilities are available using the MOBIDI MCP Server?

Call the getservices tool to list every supported system service. This tells you exactly what operations—beyond basic CRUD—your agent can automate within the MOBIDI ecosystem.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

MOBIDI MCP Server connects your AI agent directly to real-time ad campaign data. It lets you run custom queries on performance records, manage audience targeting details, and execute deep business intelligence reports for app install campaigns.

What your AI can do

Check mobidi status

Verifies the current operational connection status of the MOBIDI API.

Create record

Builds and saves a new performance or campaign record into the system's data model.

Delete record

Removes an existing, specified record from the database.

+ 9 more capabilities included

Query Campaign Data

Run specific data queries and count records across your ad campaigns based on defined criteria.

Manage Campaign Records

Create, read, update, or delete individual campaign performance records using the system's entity types.

Generate Performance Reports

List available BI reports and execute them to pull comprehensive, actionable advertising intelligence.

Inspect Data Schema

View all existing entity types and list system services to understand the data structure before querying.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

MOBIDI MCP Server: 12 Tools for Ad Ops

These twelve tools let your AI client handle every part of the mobile advertising data lifecycle—from querying basic counts to executing complex BI reports.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using MOBIDI on Vinkius

Check Mobidi Status

Verifies the current operational connection status of the MOBIDI API.

Create Record

Builds and saves a new performance or campaign record into the system's data model.

Delete Record

Removes an existing, specified record from the database.

Execute Report

Runs a specific pre-built business intelligence report and returns its output data.

Get Record By Id

Retrieves the complete details for one record when you know its unique ID.

Get Record Count

Counts the total number of records matching specific criteria (e.g., status='active').

Get Report

Retrieves metadata and details about a specific available BI report.

Get Services

Lists all the system services currently exposed by the MOBIDI platform.

List Entity Types

Retrieves a list of every recognized data structure (entity type) available in the...

List Records

Queries and returns multiple records that match complex filtering criteria across...

List Reports

Provides a list of all available, executable BI report names.

Update Record

Modifies existing fields within a specific record ID.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The MOBIDI integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "mobidi": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the MOBIDI tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"mobidi": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with MOBIDI, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MOBIDI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 12 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manually stitching together campaign performance reports is a huge time sink.

Right now, you're probably opening the ad platform dashboard. You pull down 'Customer Acquisition Cost.' Then, you open the BI tool and run a separate report for 'Conversion Rate.' Next, you copy the raw data set from one tab, paste it into Excel to calculate the final CPA metric, and then email it out. It takes three different logins, five clicks minimum, and half an hour just to get the numbers aligned.

With MOBIDI MCP Server, that process collapses. You tell your agent: 'Give me the combined campaign performance report for Q3.' The agent runs `execute_report`, pulling together data from multiple entity types and calculating the final metric in one shot. You get the answer immediately—no copy-pasting required.

MOBIDI MCP Server: Control Bidding & Audience Targeting

You used to have to log into the ad platform's UI, manually change a bid cap for an entire audience segment, and then wait hours for the system to apply the changes. If you missed a step or made a typo in the UI, your campaign could run inefficiently all day.

Now, using `update_record` through the agent, you can send that command—'Update bid cap for Audience X to $2.50'—and execute it programmatically. You gain precision and repeatability; what used to be manual, high-risk clicking is now a single, verifiable API call.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

This MCP Server hooks your AI agent up directly to real-time ad campaign data. You're dealing with performance metrics and audience targeting for app install campaigns—it’s deep stuff. It lets you run custom queries, manage records, and pull detailed business intelligence reports without ever having to log into the main platform dashboard.

Checking the System First

Before your agent runs anything, it needs to know what it's connecting to. You can use check_mobidi_status to verify the current connection status of the entire MOBIDI API. It’s quick and dirty—you just want confirmation that everything’s green. To understand the underlying structure, your agent can call list_entity_types, which spits out every recognized data structure or entity type available in the system's schema.

If you need to see what external services are exposed by the platform generally, use get_services to list all currently active system capabilities. These initial calls make sure your workflow doesn’t hit a dead end.

Querying and Inspecting Data

When you're ready to get data, you have several options for querying. You can start by calling list_reports if you want to see what pre-built intelligence reports are available before running one. If you just need a rough idea of how many records exist that match certain filters—say, all the 'active' campaigns—you run get_record_count.

For deep dives into multiple records, use list_records; this tool lets your agent query and return bulk results based on complex filtering criteria across any defined entity type. If you know exactly what record you want, skip the complexity and call get_record_by_id to pull all the specific details for one unique ID.

These tools let you gather everything from a total count of records to an entire set of filtered campaign results.

Managing Campaign Records (CRUD Operations)

This server gives your agent full control over individual performance and campaign records using standard database operations. To build out new data, your AI client executes create_record, which builds and saves a brand-new performance or campaign record into the system's main data model. When that data changes—maybe you updated an audience segment or adjusted a budget parameter—your agent uses update_record to modify specific fields within an existing record ID.

If the data is garbage, don't worry; you can use delete_record to remove any specified record from the database entirely. These four functions (create, read, update, delete) mean your AI client handles every step of campaign lifecycle management right inside the server.

Generating Intelligence Reports

For actionable business intelligence, you've got two steps. First, run get_report to retrieve metadata and details about a specific available BI report—this lets you know exactly what kind of data that report is going to pull before committing to it. Once you confirm the report details are right, your agent executes execute_report.

This runs the pre-built intelligence report and returns all the comprehensive output data you need for decision-making. You don't have to build a custom SQL query; you just tell the server which known report you want run, and it spits out actionable advertising insights.

Built · Hosted · Managed by Vinkius MOBIDI MCP Server - Ad Campaign Data Query & Management

Server ID 019dd126-b882-717a-aa47-a21e07c01e6b

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is that it lets your agent treat the ad platform like another database—you just tell it what you want and it handles the connection calls.

First, tell your agent what you need—for example, 'Get a count of active customer records.'

The agent selects and executes the relevant tool (e.g., get_record_count), passing necessary parameters like entity type.

You get back structured data or a specific count, which your AI client then uses to answer questions or drive subsequent actions.

Who is this actually for?

Data analysts, paid media managers, or BI engineers. You're the person who spends too much time jumping between the ad platform UI, SQL console, and Excel to stitch together a single performance story. You need a single entry point to get structured data quickly.

Paid Media Manager

Checks get_record_count before an optimization cycle starts, then uses execute_report to prove ROI.

Business Analyst

Uses list_entity_types first. Then runs a complex query via list_records to validate business assumptions on audience segments.

Data Engineer

Manages the data lifecycle, using create_record or update_record when raw performance logs need to be staged for modeling.

What Changes When You Connect

Full Data Control: You don't just view data; you manage it. Use create_record and update_record to stage raw performance metrics or adjust campaign parameters directly through the agent.

Instant Schema Knowledge: Don't guess what fields exist. Run list_entity_types first, then use that knowledge with list_records to craft precise, valid queries every time.

Pre-packaged Intelligence: Skip building SQL every week. Use list_reports and execute_report to run complex sales or performance analyses without writing custom code.

Status Verification: Before trusting any data pull, check the API connection using check_mobidi_status. It's a quick way to confirm everything is green for your campaign cycle.

Targeted Data Retrieval: Need one specific customer ID? Use get_record_by_id instead of querying the whole dataset. It cuts down on noise and speeds up the agent’s response.

See it in action

01 01

Validating Campaign Performance Scope

A paid media manager needs to know how many active 'Customer' records are currently linked to a campaign. Instead of running a massive, slow report and filtering the result set manually, they ask their agent: 'How many active customer records exist?' The agent runs get_record_count using the correct entity type, immediately providing the precise number (e.g., 1,234), saving minutes of dashboard clicking.

02 02

Staging Raw Ad Spend Data

A data engineer receives a CSV dump of ad spend that needs to be correlated with existing performance metrics. Rather than manually updating records, they use create_record via the agent, passing the structured data points into the correct entity type, making the raw logs immediately usable by BI tools.

03 03

Auditing a Campaign Change

A PM needs to confirm that an ad budget change made last week actually stuck. They ask their agent to get_record_by_id for the specific campaign ID. The agent pulls the current record, allowing the PM to visually verify the updated budget parameters instantly.

04 04

Comparing Reports Across Timeframes

A business analyst wants to compare last month's sales report against this month's without manual data exports. They first use list_reports to confirm the correct name, then ask the agent to execute_report, retrieving structured results for direct comparison in a single chat window.

The honest tradeoffs

Over-querying without scope

Anti-pattern

Telling your agent: 'Give me all the data.' The result is an overwhelming, massive dump of records spanning multiple entity types and potentially containing outdated or irrelevant data.

The Fix

Don't ask for everything. Always use list_records with specific filters (e.g., status='active' AND date>last_week). Or, if you just need a count, run get_record_count instead.

Assuming data structure

Anti-pattern

Trying to write an update query (update_record) for a field name that doesn't actually exist in the entity type schema, resulting in a silent failure or corrupted record.

The Fix

Check the available fields first. Use list_entity_types and then consult the system documentation (or use get_services) to verify the exact data model before attempting any write operation.

Bypassing report management

Anti-pattern

Trying to calculate a complex metric like 'Year-over-Year Growth' by manually querying dozens of tables. This is slow, brittle, and misses pre-calculated business logic.

The Fix

Let the system handle it. Use list_reports to find the correct report name, then run execute_report. You get proven business intelligence without building the query yourself.

When It Fits, When It Doesn't

Use MOBIDI if your core problem is accessing and manipulating structured performance data for mobile ads. This server gives you CRUD operations (create_record, update_record) alongside specialized reporting tools (execute_report). You should use it anytime an ad campaign's success hinges on accurate, timely data retrieval or modification.

Don't use it if your problem is general system monitoring (use a dedicated health check tool) or if you need to build entirely novel calculations that don't map to existing entity types. If the required data manipulation falls outside of standard CRUD actions—like complex predictive modeling that requires continuous, high-frequency event streaming—you might need a specialized event processing pipeline instead.

Questions you might have

How do I check if the MOBIDI MCP Server can actually connect? +

Run check_mobidi_status. This tool verifies your API connectivity right away. It's a simple, necessary step before running any other command to make sure data gets through.

What if I need to query records but don't know the entity type? +

Run list_entity_types first. This gives you an exhaustive list of all available data structures (like 'Customer', 'Order', etc.), so you can correctly target your query with list_records.

How do I run a pre-built sales report using the MOBIDI MCP Server? +

First, use list_reports to get the exact name of the report. Then, pass that name into the execute_report tool. The agent returns the structured data directly.

Can I update a record without knowing its ID? +

No, you need an ID for updates. You must first use list_records to query and find the specific records matching your criteria, then select the target ID before calling update_record.

What precautions should I take when using the `delete_record` tool in the MOBIDI MCP Server? +

You must verify deletion through a secondary audit or read operation. The server executes deletes immediately; it doesn't automatically prevent them, so always confirm your target IDs before running the command.

How do I find out what platform capabilities are available using the MOBIDI MCP Server? +

Call the get_services tool to list every supported system service. This tells you exactly what operations—beyond basic CRUD—your agent can automate within the MOBIDI ecosystem.

Does the MOBIDI MCP Server impose any rate limits on API calls? +

Yes, calling tools too frequently will trigger a specific error response indicating required wait times. Your AI client must read these HTTP codes and pause execution for reliable data retrieval.

When using `list_records` in the MOBIDI MCP Server, what filters are supported? +

The tool supports filtering records based on multiple parameters (e.g., status AND date range). Check the entity type documentation to see the exact syntax and field names needed for complex data pulls.

Can my AI run custom queries? +

Yes. list_records accepts a query object to filter and retrieve specific records from the database.

Can I create and update data? +

Yes. create_record, update_record, and delete_record provide full CRUD operations on any entity type.

Can I run BI reports? +

Yes. execute_report runs any configured report and returns the results. Use list_reports to see what is available.

Connect to your AI in seconds.

Check mobidi status

Create record

Delete record

MOBIDI MCP Server: 12 Tools for Ad Ops

Make your AI actually useful.

Check Mobidi Status

Create Record

Delete Record

Execute Report

Get Record By Id

Get Record Count

Get Report

Get Services

List Entity Types

List Records

List Reports

Update Record

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Manually stitching together campaign performance reports is a huge time sink.

MOBIDI MCP Server: Control Bidding & Audience Targeting

What your AI can actually do with this

Checking the System First

Querying and Inspecting Data

Managing Campaign Records (CRUD Operations)

Generating Intelligence Reports

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Validating Campaign Performance Scope

Staging Raw Ad Spend Data

Auditing a Campaign Change

Comparing Reports Across Timeframes

The honest tradeoffs

Over-querying without scope

Assuming data structure

Bypassing report management

When It Fits, When It Doesn't

Questions you might have