About agentstock
agentstock is a hosted remote MCP service for AI agents that offers license-clean stock images and video, with semantic search, browsing, and pay-per-use purchase.
Key features
- 01Search assets semantically
- 02Browse images and video
- 03Purchase on a pay-per-use basis
Use cases
- 01Find assets for AI-generated content
- 02Browse images or video by topic
- 03Purchase assets based on usage
MCP support
The service exposes asset search, browsing, and purchase to clients through a remote Streamable HTTP MCP endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://agentstock.dev/mcpclaude mcp add --transport http dev-agentstock-agentstock https://agentstock.dev/mcp{"mcpServers":{"dev-agentstock-agentstock":{"type":"http","url":"https://agentstock.dev/mcp"}}}Open in Cursor{"servers":{"dev-agentstock-agentstock":{"type":"http","url":"https://agentstock.dev/mcp"}}}Open in VS Code{"mcpServers":{"dev-agentstock-agentstock":{"type":"http","url":"https://agentstock.dev/mcp"}}}{"mcpServers":{"dev-agentstock-agentstock":{"serverUrl":"https://agentstock.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEagentstock
License-clean stock images and video for AI agents — semantic search, browse, and pay-per-use purchase via x402, exposed as a remote MCP server.
- Website: https://agentstock.dev
- MCP endpoint:
https://agentstock.dev/mcp(streamable HTTP)
Connect
Point any MCP client at the remote endpoint:
https://agentstock.dev/mcp
About this repo
This repository holds listing metadata only — no server source code. The MCP server runs as a hosted remote service; the manifest in server.json describes it for registry and directory ingestion.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.