Remote MCP server for searching, browsing and buying license-clean AI-generated stock images and videos, with pay-per-use purchase via x402.
What you can do
Search AI-generated images and videos semantically, or list the newest assets with an empty query
Read captions, tags, dimensions, aspect ratio, price in USDC, thumbnail, watermarked video preview, license fields and the paid download link for an asset
Fetch full metadata, license fields, price and x402 purchase instructions for a single asset id
Browse published sets of assets sold together, newest first, with set price, separate-item price and savings
Get one set with all its items, license fields and x402 purchase instructions for the whole set
When to use it
Useful when an assistant needs stock imagery or video for a project and you want license-clean, AI-generated media with clear license fields and per-asset pricing. It suits workflows where the assistant should find candidates, compare prices and then buy a specific asset or set.
Requirements
A remote MCP client pointed at the hosted streamable HTTP endpoint; nothing is installed locally. Purchases use the x402 payment flow in USDC, so a compatible wallet or payment setup is needed to download paid assets. No API keys or environment variables are declared.
Before you install
Downloads are paid: the download link requires an x402 purchase in USDC, so real money can be spent. Search results expose only watermarked previews until purchase. Review the license and release_safe fields before using an asset commercially, and check what payment details the x402 flow asks for.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/dev.agentstock%2Fagentstock/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
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.
Semantic search over AI-generated images and videos. An empty query lists the newest assets. Returns captions, tags, dimensions, aspect ratio, price in USDC, a thumbnail URL, a watermarked preview clip for videos, the paid download_url, and license fields (license, release_safe, has_text, ai_generated, ai_disclosure).
Parameterspagetypequeryper_pageaspect_ratio
get_asset
Get one asset
Full metadata, license fields, price, and x402 purchase instructions for one published asset id.
Parametersidrequired
list_sets
List asset sets
Published sets of assets that are sold together, newest first. Each set has its set price, the price of its items bought separately, the savings, every item with full metadata, and the paid download_url for the whole set.
Parameterspageper_page
get_set
Get one asset set
One published set with its items, set price, savings, license fields, and x402 purchase instructions for buying the whole set.
Parametersidrequired
Version history
1
v1.0.0LatestOct 21, 2026
Score
100%
100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.