Roboflow

Agents and crawlers that fetch a page without a browser read only the HTML response. This check looks for the page’s main content in that response.

Found: The server HTML has 1,353 characters of main content; 250 are required.

Markdown is the cheapest format for an agent to read. This check looks for a Markdown version of this page and confirms that it is the same page.

Found: method: dom-alternate; 5,862 characters

• ✓ Markdown version of this page (10/10)
• ✓ Markdown matches the page (5/5)

Evidence: https://docs.roboflow.com/readme.md (opens in a new tab) · HTTP 200

Agent tools commonly cut off long responses. This check measures the text an agent receives from this page.

Found: The Markdown version has 5,862 characters.

AI search and user-triggered fetch agents read docs when a person asks a question. This check reads robots.txt rules for those agents.

Found: 0 of 11 AI search and user-triggered fetch agents are blocked in robots.txt.

llms.txt is an index that points agents to the documentation. This check validates it, measures it, and samples its links.

Found: 2 sections, 81 links; over 131,070 characters; sampled links return Markdown

• ✓ Valid llms.txt index (7/7)
• ✗ llms.txt under 50,000 characters (0/4, missing)
• ✓ llms.txt links return Markdown (4/4)

Evidence: https://docs.roboflow.com/llms.txt (opens in a new tab) · HTTP 200

A sitemap lists every page, so crawlers do not depend on navigation to find them.

• ✓ robots.txt present (1/1)
• ✓ Sitemap declared (2/2)
• ✓ Sitemap valid XML (2/2)

Structured page metadata in the server HTML helps machines identify the page and its preferred address.

• ✗ JSON-LD in raw HTML (0/1.25, missing)
• ✓ Canonical link (1.25/1.25)
• ✓ Meta description (1.25/1.25)
• ✓ Open Graph (1.25/1.25)

A Model Context Protocol server lets agents search or use the docs through tools.

Found: present, auth required: Bearer resource_metadata="https://mcp.roboflow.com/.well-known/oauth-protected-resource/mcp", scope="workspace:read project:create project:read project:update workflow:create workflow:read workflow:update folder:create folder:read folder:update folder:delete image:create image:read image:tag image:annotate model:infer model:deploy model:manage model:compile model-eval:read workflow-evals:read workflow-evals:write workflow-evals:run workflow-evals:export device:read device:update vision-events:read vision-events:write vision-events:manage workspace-stats:read batch:create batch:read batch:admin-read batch:update batch:delete version:create version:read version:update training-job:create annotation-job:create annotation-job:read annotation-job:update annotation-job:submit-review annotation-job:review annotation-job:return-edits annotation-job:accept annotation-job:delete-annotations annotation-job:delete video-inference-job:create video-inference-job:read integration:create integration:delete credentials:create credentials:read credentials:update credentials:delete api-key:read api-key:create api-key:update api-key:revoke datasource:bucket-mirror:read datasource:bucket-mirror:write datasource:bucket-mirror:trigger data-staging:read data-staging:write data-staging:delete batch-processing:read batch-processing:trigger openid profile email"

Evidence: https://mcp.roboflow.com/mcp (opens in a new tab) · HTTP 401

A machine-readable API description lets coding agents build API calls without guessing from prose.

• ✗ OpenAPI document (0/3, missing)
• ✗ API catalog (.well-known) (0/2, missing)

Emerging standards that help agents discover and use a site.

• ✓ Content Signals (1/1)
• ✗ Agent skills index (0/1, missing)
• ✗ OAuth discovery (0/1, missing)
• ✗ Link headers (0/1, missing)
• ✗ Web Bot Auth directory (0/1, missing)
• ✗ MCP server card (0/1, missing)
• ✓ Agent login instructions (auth.md) (1/1)

llms-full.txt combines the docs into one file for tools that load a whole documentation set.

Found: no-h1

Evidence: https://docs.roboflow.com/llms-full.txt (opens in a new tab) · HTTP 200

An assistant on the docs site answers readers’ questions. It helps people, not external agents.

Found: none detected