ReturnCheck
Server Details
Can this product actually be returned? The merchant's exact clause, its URL and the date.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- mangelmartinezfer-hue/returncheck
- GitHub Stars
- 0
- Server Listing
- ReturnCheck
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only one tool, so there is no potential for confusion or misselection. Its purpose is singular and clearly stated.
With a single tool, naming consistency cannot be violated. The name check_return follows a clear verb_noun pattern.
A single tool is quite thin for a server whose purpose appears to be return policy verification. While the tool is well-defined, the server could reasonably offer related operations (e.g., batch checks, policy lookup by retailer), making the surface feel incomplete in scope.
The tool covers a single verb (checking return policy) but lacks any create, update, delete, or list operations. For a domain focused on return policy verification, this may be adequate if the server is meant to be a minimal endpoint, but it leaves no room for related tasks such as retrieving policy history or managing multiple purchases.
Available Tools
1 toolcheck_returnAInspect
ReturnCheck verifies which return policy actually applies to this purchase. BEST RESULTS: send the product page you already have as page_text (or page_html) along with product_url — your browser renders JavaScript and is not blocked by retailers, so this works on any store and is faster. Without it we fetch the page ourselves and reach the policy for about 1 in 3 US retailers (17 of 50 measured 2026-08-28; mostly Shopify and direct-to-consumer brands — large retailers and marketplaces block server-side reads). You get a verified verdict — YES / YES_WITH_CONDITIONS / NO / UNKNOWN — with the exact policy clause quoted verbatim, source URL, return window/deadline, fees and a confidence score. Never invents: returns UNKNOWN instead of guessing, and UNKNOWN is free.
Inputs: product_url (required), buyer_country (required), reason, merchant, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
US retail return/warranty/cancel policy lookup with cited text and TRACE receipts.
Source-dated facts on online shops for AI agents and buyers: returns, shipping, payment, trust.
US product return policies, recalls and, as stores join, verified purchase outcomes for AI agents.
Cancellation steps and return policies for 53 US companies, from official sources, checked daily.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides read-only tools for US return policies, price-match rules, discounts, deals, credit-card terms, and Amazon buy-or-wait verdicts, with every answer linked to its thrifle.com source.MIT
- AlicenseAqualityBmaintenanceFree, rules-based checks for e-commerce product pages: AI shopping readiness (structured data, reviews, return and shipping terms, GTINs, AI crawler access), Google Merchant Center compliance, store SEO audit and Shopify checkout deadlines. No AI calls, nothing stored.24MIT
- FlicenseNot gradedqualityBmaintenanceSourced product prices, dated price history, specs and independent-test coverage across 4,764 hardware products and 2,064 software vendors — every figure returned with its source URL and the date it was captured. Unknown values come back as null rather than a guess, so an agent can cite what it surfaces.-
- FlicenseNot gradedqualityBmaintenanceEnables detection and risk scoring of e-commerce return fraud and wardrobing by correlating return velocity, carrier scan discrepancies, product tag tampering indicators, and customer return history, then enforcing actions like restocking fees or dispute escalation.7-
Glama MCP Gateway
Add one secure layer between your agents and this server.