Docker: the 360 agent-readiness check

Docker scores 69 of 100 on Ora's agent-readiness scan, a C, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 3: an MCP server, OAuth, a command line. A live MCP handshake and six agents through the door, with no API description.

On 9 November 2026 the public site at docker.com scored 69 of 100 on Ora's agent-readiness scan, a C, in Ora's Infrastructure category. Ora probes a site the way an agent would: it requests pages with the agents' own user agents, reads robots.txt, looks for the files agents read, and tries the API, MCP and payment surfaces. This check reads the act layer first, because that is what the directory records, then the door, what an agent can read, and whether the company is found and recommended. Ora's one-line summary: Docker offers developer resource discoverability, but lacks an OpenAPI specification.

The score

What an agent can do

The surfaces an agent acts on: an API it can find and call, an MCP server, an agent card, OAuth metadata, a command line. This is the layer the directory records, so it comes first. 2 checks in this group do not apply to this site and are left out.

In the directory, Docker not counted (no answer); the connector run of 4 November 2026 is on the entry page. Ora's MCP server check for the same domain reads pass; the two look for different things, the directory for a server that answers a handshake and lists tools, Ora for a server it can find from the site.

At the door

What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents.

What an agent can read

Whether the text is in the first response, what the site publishes for agents, and how it describes itself to them.

Found and recommended

Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read.

Payments

The agent payment protocols Ora probes for. A site that sells nothing has nothing here, and Ora scores the layer out of zero when none applies. 5 checks in this group do not apply to this site and are left out.

The fixes worth most points

Ora attaches an estimate to each failing or partial check: how many points the site would gain by passing it. These are the 5 with the largest estimates for Docker, with what Ora observed. The wording of each fix is Ora's; the 28 checks it runs on an MCP server are listed with their layer and tier.

• OpenAPI spec published: fail, 0 of 7, about 3.8 points to gain. Ora saw: No OpenAPI/Swagger specification found
• Scoped permissions: fail, 0 of 5, about 3.1 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found
• WebMCP support: fail, 0 of 5, about 3.1 points to gain. Ora saw: No WebMCP support detected - no tool-attribute forms and no document.modelContext / navigator.modelContext usage found (scanned 8 of 43 same-origin script bundle(s) for modelContext registrations)
• JSON error responses: fail, 0 of 4, about 2.5 points to gain. Ora saw: API does not return JSON error responses (or no API detected)
• Public API with reachable endpoints: partial, 3 of 7, about 2.5 points to gain. Ora saw: API described in documentation at https://docs.docker.com but no machine-verifiable API surface confirmed. Best-of-protocols score: 3/7.

Our read

Docker's MCP server completed a live handshake with Ora, llms-txt version 1.26.0 over Streamable HTTP on protocol 2025-11-25, and the door is open to all six agent user agents Ora sent. The rest of the act layer is lighter than that start suggests: the API is described at docs.docker.com with no machine-verifiable surface, there is no OpenAPI specification, no declared scopes, and the endpoints Ora tried do not answer errors as JSON; OpenID Connect discovery at login.docker.com, the docker package on npm and SDKs in npm and PyPI are what counts. The reading side holds it to a C as well, with a JSON-LD block that has no identity type, a heading tree that skips from H1 to H4 and a text ratio just under 5 percent, though docs.docker.com carries an llms.txt and the domain ranks first for its agent platform term. A live server with nothing describing the API beside it.

Test your own surfaces

The scan above is free and needs no account: enter a domain at ora.ai and read the same four layers for your own site. For an MCP server, Ora scans the server URL itself and runs 28 of its 132 public checks on it, which is why it is the check this directory recommends; the reasons, the limits and the alternatives are on their own page. The command below runs the same audit from a terminal and exits with 1 under the score you set, so it can gate a deploy.

npx ax@0.10 audit https://example.com --min-score 70

All 360 checks, one company a day. Corrections to the corrections page.