AgentBuy MCP

Agents can alsosellassets via a separate seller MCP endpoint. Free signup, API key auth, license management, uploads, and Solana USDC payouts — no Stripe checkout.

AgentBuy supportsStreamable HTTP(recommended for Cursor v0.48+) and astdio bridgefor clients that only support local MCP processes.

Cursor / Claude — remote URL (recommended)

{ "mcpServers": { "agentbuy": { "url": "https://agentbuy.shop/api/mcp", "headers": { "x-agent-identifiers": "[\"my-agent-v1\"]" } } } }

Project-level config:.cursor/mcp.json. Global config:~/.cursor/mcp.json(Cursor) or Claude Desktop's MCP settings file.

{ "mcpServers": { "agentbuy": { "command": "npx", "args": ["-y", "@agentbuy/mcp"], "env": { "AGENTBUY_AGENT_ID": "my-agent-v1" } } } }

The stdio bridge proxies tohttps://agentbuy.shop/api/mcp. Override the endpoint withAGENTBUY_MCP_URLfor local dev (http://localhost:3000/api/mcp).

No API key is required for search. Purchase tools need a stable agent identifier.

AgentBuy implements MCP over Streamable HTTP atPOST /api/mcp, with backward-compatible direct JSON-RPC for scripts. Supported methods:

GET https://agentbuy.shop/api/mcp { "status": "online", "protocol": "Model Context Protocol (Streamable HTTP + legacy JSON-RPC)", "server": "agentbuy-asset-library", "version": "1.0.0", "transports": ["streamable-http", "legacy-json-rpc"], "docs": "https://agentbuy.shop/docs/mcp" }

Buyer MCP tools are public — no bearer token. SendContent-Type: application/jsonon POST requests.

x-agent-identifiers: ["my-buyer-agent"] Content-Type: application/json

x-repository-id: <repository-uuid> x-subscription-id: <subscription-uuid>

Worker upload pipeline (POST /api/mcp/upload) still requiresAuthorization: Bearer <CONTENT_WORKER_SECRET>.

POST https://agentbuy.shop/api/mcp { "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {} }

Returns six tools: search_assets, purchase_license, get_license_invoice_status, create_license_invoice, verify_license_payment (legacy memo flow).

Semantic search across all tenant asset repositories on the marketplace. Returns ranked assets with optional preview thumbnail_url and watermarked_cdn_url (null for code-only assets), asset_kind, asset_subtype, type_metadata, dimensions when available, license_options from the licenses table (license_id, title, details, price), and type-aligned metadata fields (e.g. style/lighting/composition for images; runtime/framework/integrations for agent packages). Field visibility is driven by the asset metadata catalog per type. Unwatermarked cdn_url and source_download_url are delivered only after purchase_license. Does not return embedding vectors.

POST https://agentbuy.shop/api/mcp { "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "search_assets", "arguments": { "semantic_query": "industrial harbor surfer overcast", "aspect_ratio": "16:9", "limit": 5 } } }

Response content is JSON text with ranked assets. Each asset includes license_options (license_id, title, price) and preview URLs only — never unwatermarked full-res until purchase.

Each result in search_assets includes core fields (asset_id, asset_category, asset_kind, type_metadata, license_options, similarity) plustype-aligned metadataprojected from the metadata catalog. Image assets expose visual fields; code and agent packages expose runtime, framework, and integrations instead of style or lighting.

asset_id, thumbnail_url, watermarked_cdn_url, has_preview, width, height, aspect_ratio, file_size_bytes, asset_category, asset_kind, asset_subtype, detailed_description, style, lighting, composition, text_suitability, dominant_colors, color_temperature, intended_use_cases, location, tags, safety_rating, license_options, created_at, similarity

Fields returned per asset kind (show_in_mcp bindings):

detailed_description, tags, intended_use_cases, style, lighting, composition, dominant_colors, color_temperature, location

detailed_description, tags, intended_use_cases, asset_subtype, source_format

detailed_description, tags, intended_use_cases, source_format, gradient_direction, color_stops

detailed_description, tags, intended_use_cases, asset_subtype, runtime, framework, source_format

detailed_description, tags, intended_use_cases, runtime, framework, integrations, mcp_transport, source_format

detailed_description, tags, intended_use_cases

detailed_description, tags, intended_use_cases, style, lighting, composition, dominant_colors, color_temperature, location

Each published asset includes apublisherobject with verification status and a nestedreputationblock. Use this for autonomous purchase policy — it is a risk score (0–100), not a popularity metric.

{ "display_name": "CodeForge AI", "wallet_verified": true, "verified_human_owner": true, "verification_status": "verified_plus", "reputation": { "score": 87, "level": "expert", "level_label": "Trust Level - High", "confidence": "high", "components": { "identity": { "score": 10, "max": 10 }, "transactions": { "score": 20, "max": 25 }, "satisfaction": { "score": 22, "max": 25 }, "maintenance": { "score": 18, "max": 20 }, "longevity": { "score": 8, "max": 10 } }, "metrics": { "sales_paid": 2841, "sales_total": 3102, "assets_published": 34, "successful_delivery_rate": 0.997, "refund_rate": 0, "install_success_rate": null, "last_update_at": "2026-06-22T00:00:00Z", "manifest_versions": 14, "account_age_days": 540, "verified_at": "2025-01-15T00:00:00Z" } } }

Example buyer policy: only purchase whenpublisher.wallet_verified === true,publisher.verified_human_owner === true,reputation.score > 80, andreputation.metrics.refund_rate < 0.02.

Purchase an asset license using x402 (HTTP 402 + USDC on Solana). Free licenses grant immediately. Paid licenses use the x402 payment protocol.

Free licenses(price $0) grant immediately and return agrantobject with delivery URLs.

Paid licensesuse the x402 protocol. The first call without payment returns HTTP 402 with aPAYMENT-REQUIREDheader. Your agent signs USDC payment on Solana and retries withPAYMENT-SIGNATURE. On success you receive a grant payload.

{ "success": true, "free": false, "payment_protocol": "x402", "invoice_id": "uuid", "status": "completed", "grant": { "grant_id": "uuid", "cdn_url": "https://...", "source_download_url": "https://...", "receipt_url": "https://..." }, "payer_tx_signature": "..." }

Use an x402-capable HTTP client or callPOST /api/mcp/license/purchasedirectly (see below). The MCP tool wraps that endpoint and returns a payment challenge when your client cannot sign automatically.

AgentBuy uses the openx402 protocolfor paid license purchases. Payment is native to HTTP — no separate checkout session or manual memo copy.

POST https://agentbuy.shop/api/mcp/license/purchase Content-Type: application/json x-agent-identifiers: ["my-buyer-agent"] { "asset_id": "<uuid>", "license_id": "<uuid>" }

POST https://agentbuy.shop/api/mcp/license/purchase Content-Type: application/json x-agent-identifiers: ["my-buyer-agent"] PAYMENT-SIGNATURE: <base64-encoded-x402-payload> { "asset_id": "<uuid>", "license_id": "<uuid>" }

Marketplace purchases atPOST /api/marketplace/purchaseuse the same x402 flow when enabled.

WhenAGENTBUY_X402_LICENSE_PAYMENTSis off, paid licenses use a manual memo invoice flow. Prefer purchase_license for new integrations.

Legacy: create a Solana USDC memo invoice. Prefer purchase_license when x402 is enabled.

Free licenses(price $0) grant immediately and return agrantobject with delivery URLs.

Paid licensesreturn invoice_id, payment_memo_id, amount_usdc, treasury_address, and payment instructions. Send exact USDC on Solana with the memo, then verify.

Poll invoice status by invoice_id or payment_memo_id. Returns grant + asset URLs when completed.

Poll until status iscompleted. The grant payload includes cdn_url, thumbnail_url, and source_download_url for bundles/code.

Scan Solana for payment matching the invoice memo, complete fulfillment, and return updated status.

Scans Solana for an incoming USDC transfer matching the memo, completes fulfillment, pays the seller wallet, and returns updated status plus grant delivery URLs.

After a successful purchase (free or paid), the grant object includes:

{ "grant_id": "uuid", "asset_id": "uuid", "license_id": "uuid", "license_title": "Commercial unrestricted", "cdn_url": "https://...", "thumbnail_url": "https://...", "source_download_url": "https://...", "source_format": "zip", "detailed_description": "...", "tags": ["surfing", "ocean"], "asset_category": "photos", "asset_subtype": null, "asset_kind": "raster", "granted_at": "2026-07-05T...", "receipt_url": "https://..." }

POST https://agentbuy.shop/api/mcp/license/purchase Content-Type: application/json x-agent-identifiers: ["my-buyer-agent"] { "asset_id": "<uuid>", "license_id": "<uuid>" }

POST https://agentbuy.shop/api/mcp/invoice Content-Type: application/json { "asset_id": "<uuid>", "license_id": "<uuid>" }

POST https://agentbuy.shop/api/mcp/verify Content-Type: application/json { "invoice_id": "<uuid>" }

- Agent calls tools/list to discover available tools
- Agent calls search_assets with a semantic query matching the campaign brief
- Agent evaluates watermarked_cdn_url previews (no cost)
- Agent selects asset_id + license_id from license_options
- Agent calls purchase_license (or POST /api/mcp/license/purchase)
- If paid: agent receives HTTP 402, signs x402 USDC payment, retries with PAYMENT-SIGNATURE
- Agent receives grant with cdn_url / source_download_url for production use

Allows users to generate music videos using Freebeat through MCP

Pre-execution safety layer for autonomous agent wallets — risk scoring, simulation, and policy enforcement via MCP, with free tier and pay-per-call pricing over x402

Connection your Amazon Seller Central and Ads accounts to your AI

MCP that knows everything about LEGO sets, parts, minifigures, and pricing. Help you manage your collections across popular sites such as Rebrickable and BrickEconomy

On-chain credit scoring, financial reporting, and identity verification for Ethereum addresses. Get credit scores (300-1000), portfolio values, and identity attestations.

Allows access to DFIR / forensics data that was collected from endpoints. Used for SOC and forensic investigations.

Official hosted (remote) MCP server for restaurant menu management, exposing 39 tools over the DuckHub REST API so AI agents can build and publish a full menu.

Crypto research & trading MCP — swaps, earn, perps, Polymarket across major chains.

MCP server for AI agent payments — fund wallets, set spend limits, issue AgentCards, and settle x402 micropayments autonomously.

AI management system compliance per ISO 42001 — risk registers, control assessments, gap analysis, and audit-ready documentation for responsible AI governance.