Redo MCP for AI. Process returns and claims, end-to-end, from your chat.

Q: How do I list all pending returns using Redo MCP Server?

Use the liststorereturns tool. This function retrieves a summary view of multiple claims and returns, letting you see which ones need attention at a glance.

Q: What is the difference between approvereturnclaim and processfinalresolution?

approvereturnclaim only changes the status to 'Approved.' It’s the sign-off. You must then use processfinalresolution to actually trigger the money transfer or credit.

Q: Can I calculate shipping costs for a return? Which tool do I use?

Yes, you use getreturnshippingrates. This function pulls real-time rates and multiple carrier options based on the return's origin.

Q: How do I check if an item is covered for a claim?

Call getprotectionsummary to get high-level details about your coverage rules. For specific items, use listprotecteditems to see the product list.

Q: I need to add a note to a claim; which tool is correct?

Use addinternalnote. This posts a private comment or log entry directly onto the specific return record, keeping the communication history tied to that single claim.

Q: If I need general background info on the store, which tool should I use: getstoredetails?

Use getstoredetails to fetch high-level metadata about your Redo account. This gives you general business context without needing a specific return ID or claim number.

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.

Redo manages returns, exchanges, and shipping protection claims through your AI agent. It connects your e-commerce operations to a single protocol layer, letting you track requests, calculate rates, approve claims, and process refunds without touching a dashboard.

Stop switching tabs; manage the full post-purchase lifecycle in natural conversation.

What your AI can do

Add internal note

Adds a private comment or log entry to a specific return request record.

Approve return claim

Updates a claim's status, formally approving the customer's return request.

Verify api connection

Runs a test to confirm that the MCP server is properly connected to the Redo API endpoint.

+ 9 more capabilities included

Review Claim Status

List all pending returns and protection claims, checking their current status and associated customer metadata.

Update Return Lifecycle

Programmatically update a return's status (e.g., approved or rejected) directly from your agent conversation.

Finalize Financial Resolution

Trigger final actions like refunds, store credit creation, or exchange orders for damaged/lost packages.

Determine Coverage Scope

Access detailed information about shipping protection settings and which products are eligible for claims.

Calculate Shipping Costs

Retrieve real-time shipping rates required to estimate return costs for customers or internal accounting.

Log Internal Notes

Add private comments or communication logs to any specific return or claim record for team visibility.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Redo MCP Server: 12 Tools for E-commerce Operations

This collection of tools lets your AI client manage the entire post-purchase lifecycle—from initial claim listing to final resolution and refund processing.

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 Redo on Vinkius

Add Internal Note

Adds a private comment or log entry to a specific return request record.

Approve Return Claim

Updates a claim's status, formally approving the customer's return request.

Verify Api Connection

Runs a test to confirm that the MCP server is properly connected to the Redo API...

Get Store Details

Retrieves basic metadata about the specific store or seller associated with the...

Get Protection Summary

Retrieves high-level details about current shipping protection coverage rules and...

Get Return Details

Pulls all specific metadata for a single return request, including item IDs and purchase dates.

Get Return Shipping Rates

Calculates real-time shipping costs and options available for returning packages.

List Protected Items

Lists all products that are currently covered under the shipping protection policy.

List Store Returns

Retrieves a summary view of multiple returns and claims across the store.

List Return Webhooks

Shows a list of active webhooks, confirming which internal systems receive return...

Process Final Resolution

Finalizes a return or claim by executing definitive actions, like issuing refunds or...

Reject Return Claim

Updates a claim's status, formally rejecting the customer's return request and providing a reason.

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 Redo 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": {
  "redo": {
    "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 Redo 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:

"redo": {
  "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 Redo, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ 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 Redo. 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.

Tracking returns means clicking through three different dashboards and copying IDs.

Right now, handling a single customer return is a pain. You open the support dashboard to get the claim ID. Then you jump to the shipping tab to calculate rates, then finally move to the finance portal to see if it's eligible for credit. It takes five clicks and three different logins just to answer 'What's wrong with this order?'

With Redo MCP, your agent handles the whole sequence in chat. You ask, 'Check claim ABC.' The agent runs `get_return_details`, pulls rates via `get_return_shipping_rates`, and gives you a full status report—no tab switching necessary.

Redo MCP Server: Process final resolutions with one command.

Before, finalizing a claim meant multiple hands. Someone had to approve the request, someone else had to manually trigger the refund in the finance system, and a third person had to update the customer service ticket status. It was slow and prone to human error.

Now, your AI agent manages that handoff. After you confirm details using `get_return_details`, one prompt executes `process_final_resolution`, updating the claim, triggering the refund, and logging the action—all in sequence.

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

You connect your Redo account to any AI agent using Model Context Protocol (MCP). This server gives your agent direct access to manage returns, exchanges, and shipping protection claims. You handle the entire post-purchase lifecycle—from initial request listing straight through refund processing—all in natural conversation without touching a dashboard. Stop switching tabs; you'll run the whole operation from one place.

Reviewing Claim Status
You can pull up a customer's full claim history immediately by calling list_store_returns or grabbing all specific metadata for one request with get_return_details. You'll also get basic info about the seller using get_store_details, and you'll see exactly what products are covered under policy when you use list_protected_items. To check how systems receive notifications, call list_return_webhooks to view active webhooks.

For a quick rundown of current shipping rules, run get_protection_summary. You can also get real-time cost estimates for returning packages by calling get_return_shipping_rates.

Updating the Return Lifecycle
The server lets you change a return's status directly through your agent conversation. If the customer is good to go, you call approve_return_claim; if they aren't, you reject it using reject_return_claim, providing a reason right away. You can log private comments or team notes on any record by calling add_internal_note.

Finalizing Financial Resolution
When the job is done, you finalize the action—like issuing refunds, creating store credit, or setting up an exchange for damaged goods—by running process_final_resolution. You'll want to run verify_api_connection first just to make sure your agent client can talk to the Redo API endpoint correctly.

Your AI agent uses these tools to manage returns. It doesn't just view data; it executes the operational workflow.

Built · Hosted · Managed by Vinkius Redo MCP Server - Manage Returns and Claims with AI

Server ID 019d75fd-c200-7324-9d9a-365dd9171f5c

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is you manage complex logistics workflows using simple chat prompts instead of navigating a suite of dashboards.

Subscribe to the Redo server via Vinkius Marketplace and provide your Store ID and API Secret.

Configure your AI client (Claude, Cursor, etc.) to recognize the MCP endpoints for Redo.

Instruct your agent: 'List all returns from John Doe.' The agent runs list_store_returns and presents actionable data.

Who is this actually for?

The Tier 2 Support Specialist who spends too much time clicking through multiple dashboard tabs to find one piece of claim data. The E-commerce Operations Manager who needs an instant overview of all pending resolutions across different product lines. Or the Logistics Coordinator trying to calculate return shipping costs on the fly.

Tier 2 Support Specialist

Uses get_return_details and add_internal_note constantly. They check a customer's entire claim history, decide if it needs more info, and log notes without leaving the chat window.

E-commerce Operations Manager

Runs bulk status checks using list_store_returns. They need to see which claims are pending approval so they can batch process them or investigate outliers.

Logistics Coordinator

Relies on get_return_shipping_rates and list_protected_items to advise customers quickly. They calculate the precise cost before telling the customer what to expect.

What Changes When You Connect

Stop manual dashboard hopping. Instead of checking 5 different tabs to find a return's status, use list_store_returns directly in your conversation flow.

Speed up approvals. Your agent runs get_return_details, lets you review the metadata, and executes approve_return_claim—all without copy-pasting IDs or clicking buttons.

Accurate cost estimates on demand. Need to quote a return shipment? Call get_return_shipping_rates to get current costs instantly, making your customer advice accurate every time.

Automate the resolution step. Don't just track claims; use process_final_resolution to trigger refunds or credits immediately after approval, closing the loop completely.

Full visibility into policy. Use get_protection_summary and list_protected_items to answer 'Is this covered?' questions accurately and quickly, preventing payment disputes.

See it in action

01 01

The Damaged Item Claim

A customer contacts support: 'My jacket arrived ripped.' Your agent first calls get_return_details to verify the purchase ID. Next, it uses get_protection_summary to confirm coverage. Finally, since it's damaged, the agent runs process_final_resolution to automatically generate a replacement order.

02 02

The Failed Return Attempt

A return request is submitted but lacks necessary documentation. Your agent calls get_return_details, sees the missing information, and uses reject_return_claim with a specific reason code. This prevents the customer from waiting for an invalid approval.

03 03

Checking Complex Shipping Needs

A manager needs to advise on return costs for different geographies. The agent calls get_return_shipping_rates, pulling multiple carrier options and cost breakdowns so the manager can quote the best option immediately in chat.

04 04

Auditing Past Claims

A quality assurance team needs to review all claims from a specific product line last month. They use list_store_returns to pull the batch data, then filter by status and add add_internal_note for follow-up.

The honest tradeoffs

Ignoring Initial Verification

Anti-pattern

A user gets confused and immediately calls approve_return_claim without checking if the item was actually covered or if the refund has been processed. This causes incorrect status updates.

The Fix

Always start by calling get_return_details to gather all metadata first. Then, call get_protection_summary before making any approval decisions.

Over-relying on the summary view

Anti-pattern

Reading a simple report from list_store_returns and assuming you know exactly why a claim is stuck. The list only shows status, not the root cause.

The Fix

Always drill down. Use get_return_details for any record that looks suspicious or requires investigation before taking action.

Using generic language

Anti-pattern

Telling your agent 'Fix this return.' This is too vague and forces the AI to guess which tool, if any, needs calling.

The Fix

Be precise. Tell it: 'Use process_final_resolution on ID X because the payment failed.'

When It Fits, When It Doesn't

Use this server when your returns process is high-volume and follows predictable decision paths (e.g., damaged = refund; lost = replacement). It's perfect for implementing a tiered workflow: 1) Triage (list_store_returns -> get_return_details). 2) Decision (approve_return_claim or reject_return_claim). 3) Action (process_final_resolution, add_internal_note).

Don't use this if your policies are constantly changing, requiring human legal interpretation not tied to a specific tool. If the issue requires cross-system data (like reconciling payment processor logs with Redo), you’ll need an additional integration layer outside of these tools.

Questions you might have

How do I list all pending returns using Redo MCP Server? +

Use the list_store_returns tool. This function retrieves a summary view of multiple claims and returns, letting you see which ones need attention at a glance.

What is the difference between `approve_return_claim` and `process_final_resolution`? +

approve_return_claim only changes the status to 'Approved.' It’s the sign-off. You must then use process_final_resolution to actually trigger the money transfer or credit.

Can I calculate shipping costs for a return? Which tool do I use? +

Yes, you use get_return_shipping_rates. This function pulls real-time rates and multiple carrier options based on the return's origin.

How do I check if an item is covered for a claim? +

Call get_protection_summary to get high-level details about your coverage rules. For specific items, use list_protected_items to see the product list.

I need to add a note to a claim; which tool is correct? +

Use add_internal_note. This posts a private comment or log entry directly onto the specific return record, keeping the communication history tied to that single claim.

How do I verify that my Redo API credentials are correct using the `verify_api_connection` tool? +

It runs a simple check to confirm your connection status. This tool confirms if your Store ID and Secret key work with minimal calls, so you can catch authentication errors before running critical functions.

What does the `list_return_webhooks` tool help me monitor about my return system? +

This tool lists all active webhook configurations. You use it to confirm your internal systems are correctly set up to receive real-time notifications for returns or claims, ensuring no data gets missed.

If I need general background info on the store, which tool should I use: `get_store_details`? +

Use get_store_details to fetch high-level metadata about your Redo account. This gives you general business context without needing a specific return ID or claim number.

How do I get my API Secret for Redo? +

Are shipping protection claims handled differently than returns? +

No, Redo treats shipping protection claims (for lost, damaged, or stolen items) as a specific type of return record, accessible via the same tools.

Can I approve a return request directly through the agent? +

Yes! Use the 'approve_return_claim' tool and provide the Return ID. The agent will update the status in Redo instantly.

How do I see the reasons why customers are returning items? +

The 'get_return_details' tool retrieves the full metadata for any request, which includes the specific return reason code and customer comments.

Connect to your AI in seconds.

Add internal note

Approve return claim

Verify api connection

Redo MCP Server: 12 Tools for E-commerce Operations

Make your AI actually useful.

Add Internal Note

Approve Return Claim

Verify Api Connection

Get Store Details

Get Protection Summary

Get Return Details

Get Return Shipping Rates

List Protected Items

List Store Returns

List Return Webhooks

Process Final Resolution

Reject Return Claim

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

Tracking returns means clicking through three different dashboards and copying IDs.

Redo MCP Server: Process final resolutions with one command.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

The Damaged Item Claim

The Failed Return Attempt

Checking Complex Shipping Needs

Auditing Past Claims

The honest tradeoffs

Ignoring Initial Verification

Over-relying on the summary view

Using generic language

When It Fits, When It Doesn't

Questions you might have