mcpField
D
Dockerhub

Dockerhub

Remote
pipeworx.ioDeveloper Tools0Updated 4d ago

About Dockerhub

Dockerhub is an MCP server wrapping the Docker Hub v2 API for users searching for and checking container images. It provides repository and tag information, including platform and architecture details for a tag; public data requires no authentication.

Key features

  1. 01Search container images by keyword
  2. 02Retrieve repository metadata
  3. 03List image tags and push dates
  4. 04Inspect tag platforms and architectures

Use cases

  1. 01Find container images for deployment
  2. 02Check repository details before pulling an image
  3. 03Verify whether a tag supports an architecture

MCP support

It exposes Docker Hub image search, repository details, tag listing, and specific tag detail tools to MCP clients. It can connect through the Pipeworx gateway or run locally over stdio.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/dockerhub/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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 README

mcp-dockerhub

Docker Hub MCP — wraps the Docker Hub v2 API (free, no auth required for public data)

Part of Pipeworx — an MCP gateway connecting AI agents to 1878+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
search_imagesSearch Docker Hub for container images by keyword. Returns repository name, description, pull count, star count, and official status. Use when finding images for deployment.
get_imageGet detailed metadata for a Docker Hub repository: description, pull count, stars, last updated date, and official status. Use before pulling an image to verify quality and currency.
get_tagsList available tags for a Docker image sorted by recency. Returns tag name, digest, size, and push date. Use to find and select specific versions to pull.
get_tag_detailsGet full details for a SPECIFIC image tag, including every platform/architecture it supports (os/arch/variant), per-platform digests and sizes, the multi-arch manifest digest, and push date. PREFER for "does README image: have an arm64 build", "what platforms does README image: support", "the digest/size of README image:", multi-arch verification.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "dockerhub": {
      "url": "https://gateway.pipeworx.io/dockerhub/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/dockerhub/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1878+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/dockerhub_search_images \
  -H 'Content-Type: application/json' \
  -d '{"query":"nginx"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/dockerhub_search_images. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "dockerhub": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-dockerhub"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-dockerhub

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Dockerhub data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

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.