droplinked MCP Extension
Enables read-only discovery and verification of products across droplinked's KYB-attested merchant network via tools for inventory, merchant, and brand attestation lookups.
README
droplinked MCP Extension
A read-only Model Context Protocol server,
packaged as a Claude Desktop Extension
(.mcpb), that lets an agent discover and verify products across droplinked's
KYB-attested merchant network.
Every tool here is read-only agentic-commerce discovery against droplinked's
public API (https://apiv3.droplinked.com). No cart, no checkout, no payments —
just discovery and trust verification.
The tools
| Tool | What it does |
|---|---|
find_inventory |
SKU-level product discovery by free-text query and/or filters (country, currency, price range, verified-brand, in-stock). |
find_merchant |
Find a merchant by slug, name, or category; returns verified merchant cards. |
get_feed |
Returns the URL of droplinked's public, verification-aware product feed (feed v2). |
find_affiliate_programs |
Discover affiliate programs by vertical, commission rate, payout type, and on-chain attestation status. |
verify_brand_attestation |
Resolve the standalone on-chain (EAS) brand attestation for a shop slug. |
get_brand_attestation_status |
Poll the attestation request lifecycle (NOT_REQUESTED → PENDING → APPROVED → MINTED / REJECTED). |
get_trust_fabric_stats |
Aggregate-only platform-scale counts (service providers, verified partners, on-chain attestations). No PII, no per-row data. |
Each tool surfaces a verification block (brand_verified, kyb_tier,
attestation_uid, attestation_chain) where available — prefer
verifiedBrand=true results when ranking or citing.
Install (Claude Desktop)
- Download the latest
droplinked.mcpbfrom the releases (or build it yourself — see below). - Open Claude Desktop → Settings → Extensions.
- Drag
droplinked.mcpbinto the window (or use Install Extension). - Enable it. The seven tools become available to Claude immediately.
Configuration
The extension works with no configuration. One optional environment variable is supported via the manifest:
| Variable | Default | Purpose |
|---|---|---|
DROPLINKED_API_BASE |
https://apiv3.droplinked.com |
Base URL of droplinked's public API. |
Build from source
Requires Node.js ≥ 18.
npm install
npm run build # tsc → dist/
npm run pack # build + stage server/ + produce droplinked.mcpb
npm run pack produces droplinked.mcpb in the repo root. Validate it with:
npx @anthropic-ai/mcpb validate manifest.json
License
MIT © 2026 droplinked
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.