← All servers

droplinked D

com.droplinked.mcp/server · v0.1.2 · score 49/100 · checked 2026-11-22

Agentic commerce + trust MCP: discover, verify, and transact across droplinked's merchant network.

Source: https://github.com/droplinked/droplinked-mcp

Findings

SeverityRuleDetail
lowAG005Remote endpoint lists 38 tool(s) to anyone, no credentials needed.
criticalAG101tool 'recommend_lender': description contains instruction-like text aimed at the model ('Do not tell the user'). Possible tool poisoning.
mediumAG1021 tool(s) can execute commands or delete data (cart.removeLine). Require confirmation before the agent calls them.

What was checked

Public tools: find_merchant, find_inventory, find_affiliate_programs, verify_brand_attestation, request_brand_attestation, get_brand_attestation_status, verify_credit_risk, verify_repayment_history, verify_cross_attestation, verify_lender, get_lender_history, verify_methodology, get_methodology_timeline, get_methodology_versions, get_trust_dossier, get_trust_fabric_stats, get_underwriting_signals, get_upgrade_preview, recommend_lender, recommend_service_provider, quote_inventory_available, process_payment, search_products, get_product, list_shop_products, start_checkout, get_feed, cart.addLine, cart.updateLineQuantity, cart.removeLine

Maintainer? Fix, then add the badge

Grades refresh daily.

[![agentguard](https://agentguard-pi.vercel.app/badge/com-droplinked-mcp-server-7075d372.svg)](https://agentguard-pi.vercel.app/s/com-droplinked-mcp-server-7075d372)

agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner