Segment Connector for AI agents.
7 live capabilities
Audit your customer data pipelines and tracking schemas via chat.
Waiting for input…
Why people use Segment
Segment for Auditing Data Pipeline Schemas
With this Connector, you just ask your agent to pull the tracking plan for a specific event. It gives you the payload structure immediately in your chat window, letting you move on to writing code instead of navigating menus.
What Vinkius changes
You get a direct line of sight into your Segment infrastructure through a chat interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Verifying a new event schema
A developer needs to know the exact payload for a 'Checkout Completed' event.
- Real-world use case 02
Mapping data flows for growth
A growth lead wants to know if the 'iOS App' source is sending data to the 'Facebook Ads' destination.
- Real-world use case 03
Auditing warehouses for compliance
A privacy officer needs a list of all active data warehouses to check for storage compliance.
Complete set · 7capabilities
The complete Segment capability set.
These are the exact actions your AI can choose when you ask it to work with Segment.
01—04
4 capabilities in this set.
Part of 7 available through Segment.
- 01 Capability
Get source
Get the details of a specific data source. Use this to see exactly how a single data stream is configured.
- 02 Capability
List destinations
List all destinations for a specific source. This helps you verify where data is being routed from a specific entry point.
- 03 Capability
List sources
List all data sources in your workspace. Use this to get a full inventory of your data origins.
- 04 Capability
Get tracking plan
Get the details of a specific tracking plan. This is how you see the required schema for a specific event type.
05—07
3 capabilities in this set.
Part of 7 available through Segment.
- 05 Capability
List tracking plans
List all tracking plans in the workspace. This lets you see every available event schema in your system.
- 06 Capability
List warehouses
List all configured data warehouses. Use this to confirm which data storage systems are active.
- 07 Capability
Get workspace
Get information about your current Segment workspace. Use this to get a high-level overview of your environment.
Set up in minutes
One URL. Then ask Segment to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Segment from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Segment, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Segment for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Segment URL.
- Step 03
Save and start
Save the connection and enable Segment in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"segment": {
"url": "https://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Segment
Open Agent mode in chat and ask: "Using Segment, help me...". 7 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"segment": {
"url": "https://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Segment
Ask Copilot: "Using Segment, help me...". 7 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"segment": {
"url": "https://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Segment
Open Cascade and ask: "Using Segment, help me...". 7 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"segment": {
"url": "https://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Segment
Ask Cline: "Using Segment, help me...". 7 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add segment --transport http "https://edge.vinkius.com/vk_preview_oCSWGNyPpMslZfXLGFWI7A5SYVuHGSeAvjoUSWuf/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Segment
Ask Claude: "Using Segment, show me...". 7 tools are ready
Where the request belongs
Work Segment can move forward.
This is for data engineers and growth ops who are tired of digging through complex dashboard menus to find simple configuration details or schema requirements.
Data Engineer
Checks tracking plans on a Tuesday afternoon to ensure the frontend team is sending the correct data types.
RevOps Manager
Maps out data flows to make sure a new marketing capability is actually receiving data from the main app source.
Analytics Analyst
Quickly looks up source IDs to configure a new BI dashboard parameter without asking the engineering team.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsHevo Data (ETL & Data Pipeline)
Manage data pipelines via Hevo. list pipelines, monitor destinations, and track usage.
Integrate.io (ETL & Data Integration)
Manage data pipelines via Integrate.io. list pipelines, monitor job runs, and audit data transformations.
Portable.io
Manage your Portable ETL pipelines directly via your AI agent. monitor flows, sync runs, and destination details seamlessly.
Fivetran
Manage data movement via Fivetran. monitor connectors and destinations, handle groups, track sync states, and audit users directly from any AI agent.
Stitch Data
Automate data pipelines via Stitch. manage sources, destinations, and push data directly to your warehouse from any AI agent.
RudderStack
Connect your AI assistant natively to RudderStack to effortlessly monitor global data sources, trace routing connections, and audit enterprise marketing audiences via structured text commands.
Bring your own AI
Change the model, client or framework. Keep Segment connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Segment.
The practical details behind the request, access and result.
Can the Segment MCP help me check my data schemas?
Yes. You can ask your agent to pull up specific tracking plans to see the exact payload structure required for any event in your system.
How does the Segment MCP map my data pipelines?
It allows your agent to list all your data sources and the destinations they route to, giving you a clear view of your entire data flow.
Can I use the Segment MCP to see my active warehouses?
Yes. You can ask the agent to list all the data warehouses currently configured in your Segment workspace to check your storage connections.
Is the Segment MCP good for auditing my CDP connections?
It's perfect for auditing. You can quickly verify which sources are active and where they are sending data without manually clicking through the dashboard.
Can the Segment MCP help me find specific source IDs?
Yes. You can ask your agent to list all sources or get the details of a specific one to find the IDs you need for your analytics capabilities.
Can the AI create new sources or configure tracking events?
No. By design, this Connector uses read-only capability endpoints (list, get). It's engineered strictly to audit, report, and ingest context about your existing architecture to ensure absolute safety and prevent accidental destructiveness.
Can it tell me which downstream destinations are linked to a specific source?
Absolutely. You can prompt the AI: 'List all destinations tied to the Web App Source [ID]'. Using the list_destinations capability, the agent parses the explicit router table to confirm exact capabilities receiving your events.
Why use an AI agent to read tracking plans?
Because it radically accelerates coding. If you are developing a new feature in Cursor and need to dispatch tracking info, simply invoke the get_tracking_plan capability. The AI reads the exact structural interface from Segment and writes perfectly matching telemetry code, avoiding human typos.
One connection away
Give your agent a direct line to Segment.
Connect Segment once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available