Data Lineage Tracker Connector for AI agents.
4 live capabilities
Track and audit data provenance in LLM pipelines
Waiting for input…
Why people use Data Lineage Tracker
Solve LLM data traceability issues with Data Lineage Tracker
With this MCP, you stop guessing. Every time your agent modifies data, the change is recorded in a structured graph. You get a clear, mathematical record of the entire journey, making it easy to see exactly where a piece of information originated and how it changed along the way.
What Vinkius changes
You get a verifiable, hash-backed map of every data change in your LLM workflows.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Auditing automated content generation
An engineer needs to prove that a generated summary was derived from a specific, approved document rather than hallucinated data.
- Real-world use case 02
Debugging broken LLM pipelines
A developer uses the history of a data item to find exactly which transformation step introduced an error in the final output.
- Real-world use case 03
Meeting strict data compliance standards
A compliance officer verifies that sensitive data underwent the mandatory anonymization steps before being processed.
Complete set · 4capabilities
The complete Data Lineage Tracker capability set.
These are the exact actions your AI can choose when you ask it to work with Data Lineage Tracker.
01—04
4 capabilities in this set.
Part of 4 available through Data Lineage Tracker.
- 01 Capability
Find downstream impact
Identifies all data items that were derived from a specific source item
- 02 Capability
Register transformation
Ensure the parentId exists. Records a new step in the data lifecycle, linking a new data item to its parent
- 03 Capability
Trace item lineage
Provides the complete ancestral history of a specific data item to verify its origin
- 04 Capability
Verify item integrity
Checks if a data item's current state matches its recorded deterministic hash
Set up in minutes
One URL. Then ask Data Lineage Tracker to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Data Lineage Tracker 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_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Data Lineage Tracker for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker URL.
- Step 03
Save and start
Save the connection and enable Data Lineage Tracker in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"data-lineage-tracker": {
"url": "https://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker
Open Agent mode in chat and ask: "Using Data Lineage Tracker, help me...". 4 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"data-lineage-tracker": {
"url": "https://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker
Ask Copilot: "Using Data Lineage Tracker, help me...". 4 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"data-lineage-tracker": {
"url": "https://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker
Open Cascade and ask: "Using Data Lineage Tracker, help me...". 4 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"data-lineage-tracker": {
"url": "https://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker
Ask Cline: "Using Data Lineage Tracker, help me...". 4 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add data-lineage-tracker --transport http "https://edge.vinkius.com/vk_preview_2JD3BLLTsmdBLJ9xBNkQXDG7ISJM9DAczMPHl05p/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 Data Lineage Tracker
Ask Claude: "Using Data Lineage Tracker, show me...". 4 tools are ready
Where the request belongs
Work Data Lineage Tracker can move forward.
This is for engineers and compliance officers who can't afford 'black box' data processing in their AI pipelines.
MLOps Engineer
Monitoring the integrity of data as it flows through complex, multi-stage LLM pipelines.
Compliance Officer
Verifying that data processing meets regulatory requirements and audit standards.
Data Architect
Designing traceable workflows where the provenance of every output must be known.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDelio
Automate wealth management workflows via Delio Core OS. manage deals, investors, portfolio transactions, compliance forms, and platform users from any AI agent.
SOX Compliance Cost Estimator
Estimate the annual costs of Sarbanes-Oxley (SOX) compliance for pre-IPO companies.
Dependency License Compliance Checker
Audit software dependencies against approved SPDX license identifiers to ensure supply-chain compliance.
Comparison Copy Fairness Scorer
Audit marketing copy and comparison tables for claim verifiability, feature balance, and disparagement risk.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Data Lineage Tracker 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 Data Lineage Tracker.
The practical details behind the request, access and result.
How does Data Lineage Tracker help with LLM auditing?
It creates a permanent, hash-based record of every change made to your data, allowing you to prove exactly how an output was generated.
Can I use Data Lineage Tracker to debug my AI workflows?
Yes. You can use it to trace the history of any data item to find exactly which step in your pipeline caused an error or unexpected change.
Is Data Lineage Tracker compatible with my existing AI client?
Yes, as long as your client is MCP-compatible, like Claude, Cursor, or Windsurf, you can connect it and start tracking data immediately.
How does this MCP ensure data hasn't been tamexcepted?
It uses deterministic hashing for every transformation, meaning any change to the data would result in a different hash, making the history verifiable.
Can I verify if my data processing meets specific rules?
Yes, you can check your data against required transformation steps to ensure your pipeline is following your defined compliance rules.
How do I record a new data transformation?
You can use the trace_transformation capability to record a new step in the data's journey, providing the input ID, transformation type, parameters, and the resulting output data.
How can I verify if a piece of data is an ancestor of another?
Use the verify_provenance capability to confirm if a specific source item is part of the lineage for a target item.
Can I check if my data pipeline meets compliance requirements?
Yes, the check_compliance_audit capability allows you to validate that a data item's lineage includes all required transformation steps.
How can I verify if a data item has been altered?
You can use the verify_item_integrity capability. By providing the item ID and its current content, the system checks if the content matches the original deterministic hash recorded during transformation.
How do I see the history of a specific piece of data?
Use the trace_item_lineage capability with the specific itemId. This will return a chronological list of all transformations that led to that item.
What happens if a model produces a hallucination?
You can use find_downstream_impact with the sourceId of the hallucinated item. This identifies all descendant data items that were derived from that specific error.
One connection away
Give your agent a direct line to Data Lineage Tracker.
Connect Data Lineage Tracker once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available