mcpField
S
Stockflow Mcp

Stockflow Mcp

Local
github.com/NmediaCloudMedia & Design0Updated 17w ago

About Stockflow Mcp

Stockflow Mcp is an MCP server for finding royalty-free stock images and 4K videos from Stockflow.media. It helps people creating presentations, videos, websites, and mockups search assets and use watermarked previews before licensing full-resolution files.

Key features

  1. 01Search images and videos by keyword
  2. 02Filter by category and aspect ratio
  3. 03Browse categories and asset counts
  4. 04Retrieve asset details by File_ID
  5. 05Download watermarked previews

Use cases

  1. 01Find a calm ocean image for a presentation
  2. 02Locate coffee shop b-roll for a video
  3. 03Preview stock media in a website mockup

MCP support

It exposes search, category, asset-detail, and preview-download tools to MCP clients. The public catalog can also be queried without MCP.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"stockflow": {
"command": "npx",
"args": [
"-y",
"stockflow-mcp"
]
}
}
}
Run commandnpx -y stockflow-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmstockflow-mcp

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
querystringYesKeywords, e.g. 'ocean waves calm' or 'coffee latte'
typeenumNoRestrict to images or videos (default any)image | video | any
categorystringNoOptional category/collection filter, e.g. 'Background' or 'Microscopic'
aspectenumNoAspect ratio filter (default any)16:9 | 9:16 | 1:1 | any
limitintegerNoMax results (default 12)

Details

From the project README

stockflow-mcp

Search & use 18,000+ royalty-free stock images and 4K videos from Stockflow.media inside your AI assistant — Claude Code, Cursor, OpenCode, Codex CLI, Antigravity, or any MCP-compatible tool.

Building a presentation, video, website or mockup? Ask your assistant for "a calm ocean background" or "coffee shop b-roll" and it finds matching assets, embeds the watermarked previews (free for drafts), and gives you the link to license the full-resolution file (one-time, from $1, royalty-free forever).

No API key. The catalog is public.

Tools

ToolWhat it does
search_assetsKeyword search with type (image/video), category and aspect (16:9 / 9:16 / 1:1) filters
get_categoriesList categories with covers + counts
get_assetFull details for one asset by File_ID
download_previewSave a watermarked preview locally for embedding in a project

Install

Claude Code (as a plugin — includes the skill)
/plugin marketplace add NmediaCloud/stockflow-mcp
/plugin install stockflow-assets@stockflow
Claude Code (MCP only)
claude mcp add stockflow -- npx -y stockflow-mcp
Cursor / Windsurf / Cline (mcp.json)
{ "mcpServers": { "stockflow": { "command": "npx", "args": ["-y", "stockflow-mcp"] } } }
OpenCode (opencode.json)
{ "mcp": { "stockflow": { "type": "local", "command": ["npx", "-y", "stockflow-mcp"] } } }
OpenAI Codex CLI (~/.codex/config.toml)
[mcp_servers.stockflow]
command = "npx"
args = ["-y", "stockflow-mcp"]
Google Antigravity / Gemini CLI

Add an MCP server with command npx -y stockflow-mcp in the agent's MCP settings.

No MCP at all?

Any agent can use the public catalog directly — see llms.txt and the compact search index.

Skill only (no server)

Copy skills/stockflow-assets/ into ~/.claude/skills/ — it teaches the agent to query the public catalog JSON with plain fetches.

Licensing

Previews are watermarked and free for drafts/mockups. Production use requires a license bought on the asset's page (https://stockflow.media/gallery/a/<id>.html). Full terms: https://help.stockflow.media/license/

MIT-licensed server. Catalog content © NMedia Services & Stockflow.media.

Comments

Markdown supported

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.