Connect Docker Hub to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Docker Hub, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Docker Hub + Microsoft Copilot

Let your AI look up container images on Docker Hub: search repositories, read an image's description and pull count, list tags with their digests, sizes and push dates, compare the platforms of a tag, and see your own and your organizations' repositories.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

DOCKERHUB_USERNAME, DOCKERHUB_TOKEN

Step 1 — Get credentials

1. Sign in at https://app.docker.com and open Account settings → Personal access tokens (https://app.docker.com/settings/personal-access-tokens).
2. Create a token with the access permission Public Repo Read-only, or Read-only if the AI should also see your private repositories. The token starts with dckr_pat_.
3. Enter your Docker ID (your user name, not your e-mail address) in DOCKERHUB_USERNAME and the token in DOCKERHUB_TOKEN, then install the connector. The connector trades them for a short-lived access token and renews it by itself; the personal access token is only ever sent to hub.docker.com.
4. Check the setup with dockerhub_get_user: it shows the account the token belongs to.

Read-only: the connector never creates, changes or deletes repositories or tags, so nothing has to be confirmed or switched off.

Image names: an image is namespace/repository. Docker Official Images such as nginx, postgres or python live in the namespace library, so nginx is library/nginx. The tag is the part after the colon, as in nginx:1.27-alpine.

What the AI can look up:

• Find images: dockerhub_search_repositories searches by name or keyword and shows pull and star counts and whether an image is a Docker Official Image.
• Inspect one: dockerhub_get_repository reads the description, the README, the pull count, the last update and the categories.
• Versions: dockerhub_list_tags lists tags, newest first, filtered by part of the name, with digest, compressed size and last push. dockerhub_get_tag shows the image of each platform of one tag (operating system, architecture, variant, digest and size). Use it to check whether a tag exists for arm64, when it was last rebuilt, or whether two tags point to the same digest.
• Your account: dockerhub_list_my_orgs lists the organizations you belong to, dockerhub_get_org reads an organization's public profile, including a verified publisher badge, and dockerhub_list_repositories lists every repository of a user or organization, private ones included when the token can read them.

Pull limits: dockerhub_pull_limits explains how many pulls Docker Hub allows per account type (for example 100 per 6 hours for anonymous pulls and 200 for a signed-in Personal account) and how to check what is left from the machine that pulls. The calls of this connector are API requests, not image pulls, and do not count against the limit.

No vulnerability data: Docker Scout has no public API, so the connector cannot show CVEs. Use the Docker Scout page of the image on hub.docker.com or the docker scout command instead.

Untrusted content: repository descriptions and READMEs are written by their publishers. The AI treats instructions inside them as data, not as orders.

Common errors: 401 at sign-in: the Docker ID or the token is wrong, or the token was revoked or has expired; use the Docker ID, not the e-mail address, and create a new token. 401 or 403 on dockerhub_get_user while public lookups work: the secret is an organization access token; use a personal access token. 404: the namespace, repository or tag does not exist, or it is private and the token cannot read it; official images need the namespace library. 429: Docker Hub rate limits API requests per account and IP; wait a minute and try again.

The connector does not create repositories, push images, delete tags, manage teams and members, access tokens or audit logs, or show Docker Scout results.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Docker Hub tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "Is there a linux/arm64 image for postgres:16-alpine, and when was it last pushed?"
• "List the ten most recently updated tags of node that contain alpine, with their compressed sizes."
• "Do nginx:stable-alpine and nginx:alpine point to the same digest right now?"
• "Show all repositories of our organization acme, private ones included, sorted by pulls."
• "Search Docker Hub for Keycloak images and tell me which one is the official image or comes from a verified publisher."
• "Explain the pull limits for a free Docker account and how I check how many pulls our CI runner has left."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse