OKF export for agent-ready site knowledge bundles.

Run this report from the CLI, an MCP client, or application code. Every surface uses the same report definition and returns the same evidence. JSON is the source of truth; Markdown makes it readable without hiding dates, limits, warnings, or skipped work.

What this report helps you decide

Which crawled pages and relationships should form a limited site knowledge pack?

• An agent needs a local, reviewable site map with source citations.
• The crawl is current enough for the task.

Command facts

Report id

okf-build

Execution

Local process

Outputs

JSON and Markdown

Example parameters

reportId, maxConcepts, includeFiles, title

Agent discovery

seo reports describe okf-build --json

Interactive prompts

Human CLI commands only

When this report is not the right tool

These cases need a different report, more evidence, or a human decision. Do not force this report to answer a question its data cannot support.

• You need to check an edited or generated OKF file set for broken structure and references. Recommended report: Validate an OKF knowledge pack. Run OKF validation on the exact files. It checks supported frontmatter, paths, headings, links, citations, and manifest references without rebuilding the pack.
• You need to prove that every statement in the knowledge pack is current and correct. No automated report can verify the truth of every extracted statement. Use this build to retain source-page references, then have a person compare important claims with the current live pages and the intended site meaning.

Data sources and inputs

• Saved or fresh crawl report. Provides page URLs, metadata, internal links, extracted concepts, and crawl caveats.
• Concept and file limits. Bounds the manifest and optional inline Markdown files for the agent context available.

What this report checks

• Selects concepts and source pages consistently within the requested limits.
• Builds the OKF manifest, file paths, citations, and validation result from the selected crawl evidence.

How it works

• Selects concepts and pages within explicit limits, emits a manifest, and can include limited Markdown files.

The JSON result keeps dates, thresholds, limits, skipped work, and source completeness beside the finding. Missing, partial, capped, filtered, and complete data remain different states.

Run the report from the CLI

Build a limited site knowledge pack from a saved crawl. Agents and CI should inspect the live schema before their first run.

seo okf export --project example

seo reports describe okf-build --json

seo reports run okf-build --params '{"reportId":"crawl_example_20260710","maxConcepts":25,"includeFiles":true,"title":"Example site knowledge"}' --json

Project profiles can fill supported property and analytics inputs for the human-facing commands. The catalog form shown here is explicit by design, so agents and CI jobs do not prompt or guess.

How an MCP agent should use it

Call seo_describe_report first so the agent sees when this report is useful and gets the current input schema. Then callseo_run_report with the validated parameters. Read the status, warnings, source limits, and skipped sections before acting on a finding.

{
  "id": "okf-build"
}

{
  "id": "okf-build",
  "params": {
    "reportId": "crawl_example_20260710",
    "maxConcepts": 25,
    "includeFiles": true,
    "title": "Example site knowledge"
  }
}

Use a follow-up report returned by the result instead of guessing the next tool. The local MCP server and CLI use the same report definition and evidence. Their outer transport envelopes differ.

Use the report in a TypeScript app

Install seo as a project dependency, then call the same report catalog used by the CLI and MCP. executeReportrejects an unknown report id or invalid parameters. Provider and runtime failures come back as structured results withisError set.

npm install seo

import { executeReport } from 'seo/mcp'

const result = await executeReport(
  'okf-build',
  {
  "reportId": "crawl_example_20260710",
  "maxConcepts": 25,
  "includeFiles": true,
  "title": "Example site knowledge"
},
)

console.log(result)

The TypeScript library guide also covers direct core functions, schema discovery, and the difference betweenexecuteReport and runReport.

What comes back and how to read it

• A compact OKF manifest with concept counts, source references, file paths, and inherited crawl caveats.
• Optional limited Markdown files plus a validation result when inline files are requested.
• Treat the output as a derived local artifact. Follow citations back to the live page before using a claim.

Start with dataStatus, source details, warnings, and caveats. Then inspect the observed evidence before derived findings or suggested actions.

What this report cannot tell you

• The pack inherits the crawl scope, extraction limits, and freshness of its source report.

What to do next

1. Validate the generated files.
2. Rebuild after meaningful information architecture changes.

Related reports

• Validate an OKF knowledge pack. Check OKF files for structural, path, link, citation, and manifest problems before an agent or automation relies on them.
• Crawl a site for technical SEO issues. Map a limited part of a site, run the maintained technical checks, and save a reusable evidence baseline.

Browse all reports in Crawling and technical checks.