# uprank

> uprank is an editorial control room for evidence-backed content: it researches, drafts, scores and publishes articles for your own site, with every claim traced to a source gathered before drafting and nothing published until it clears hard quality gates.

- What it is: a multi-tenant web app that researches, drafts, scores and publishes articles for a company's own site.
- Who it is for: teams that need brand-safe, cited articles on their own blog, not content volume.
- Pipeline: brand profile → research into an Evidence Pack → brief → draft → claim check → scoring → revision → CMS draft.
- Quality: 11 scored dimensions and 13 hard gates; an article that fails any gate cannot be published.
- Publishing: Strapi, as drafts by default. Draft creation is idempotent; live publishing needs an explicit confirmation and is audited.
- Agents: a remote MCP server (streamable HTTP, bearer token or OAuth) with 17 tools; a connection sees the ones its scopes allow, and live publishing needs a hand-issued credential. Guides for Claude Code, Codex, Cursor, Windsurf, VS Code (Copilot), OpenCode.
- What it does not do: promise rankings, invent citations, fake first-hand expertise, or publish an article that fails a hard gate.

## Quality gates

An article that fails any of these cannot be approved, pushed to a CMS or published. There is no minimum overall score.

- Evidence ≥ 85
- Information gain ≥ 70
- Practical value ≥ 75
- Brand fit ≥ 80
- Readability ≥ 75
- Risk ≤ 20
- No invented citations: Every citation must point to a source in the article’s Evidence Pack, gathered before drafting.
- No broken required links: Every cited link is checked each time the article is scored, before it can be published.
- High-risk claims are supported: Each high-risk claim is checked against its source; any unsupported or contradicted one blocks the article.
- Time-sensitive claims are fresh: Claims that depend on dates, prices or versions must fall inside their freshness window.
- At least one information-gain element: For example a decision framework, worked example, checklist, comparison, template or labelled research synthesis.
- Licensed images only: Every external image carries license metadata.
- Unique title: No other article on the same site may use the same title (ignoring case and extra spaces), checked each time the article is scored.

## Docs

- [How uprank scores articles](https://uprank.devino.ca/quality-gates): the quality dimensions, weights and hard gates ([Markdown version](https://uprank.devino.ca/quality-gates.md))
- [How to fact-check AI content before you publish](https://uprank.devino.ca/how-to-fact-check-ai-content): a step-by-step method for fact-checking any AI draft, and which gates automate each step
- [An AI writer that doesn't hallucinate sources](https://uprank.devino.ca/ai-writer-that-doesnt-hallucinate): why AI writers invent sources, and what uprank refuses to publish
- [AI blog writer for Strapi: fact-checked drafts in your CMS](https://uprank.devino.ca/strapi-ai-blog-writer): how uprank connects to Strapi 5: field mapping, body formats, draft-only pushes, limits
- [FAQ](https://uprank.devino.ca/faq): product, agents, tokens, publishing
- [Full text](https://uprank.devino.ca/llms-full.txt): every public page in one Markdown file

## Agents

- [Add to Claude](https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Uprank&connectorUrl=https%3A%2F%2Fuprank.devino.ca%2Fapi%2Fmcp): fastest for Claude (web, Desktop, mobile): opens Claude's Add custom connector dialog with the uprank MCP server filled in (OAuth sign-in, no token)
- [Agent setup prompt](https://uprank.devino.ca/agent-setup/prompt.md): paste-and-run instructions for coding agents
- [Agent setup guides](https://uprank.devino.ca/agent-setup): how to connect each agent by hand
- [Claude Code setup](https://uprank.devino.ca/agent-setup/claude-code): One CLI command registers the remote MCP server for the current user.
- [Codex setup](https://uprank.devino.ca/agent-setup/codex): Register the server with the Codex CLI; the bearer header is read from the env var.
- [Cursor setup](https://uprank.devino.ca/agent-setup/cursor): Add the server to the global MCP config (or .cursor/mcp.json in a project).
- [Windsurf setup](https://uprank.devino.ca/agent-setup/windsurf): Add the server to the Cascade MCP config.
- [VS Code (Copilot) setup](https://uprank.devino.ca/agent-setup/vscode): Add an HTTP server entry to the workspace .vscode/mcp.json.
- [OpenCode setup](https://uprank.devino.ca/agent-setup/opencode): Add a remote MCP entry to opencode.json.
- [MCP endpoint](https://uprank.devino.ca/api/mcp): streamable HTTP, bearer token or OAuth (MCP authorization with dynamic client registration)

## Optional

- [Create a workspace](https://uprank.devino.ca/signup)
- [Privacy policy](https://uprank.devino.ca/privacy): what uprank collects, who receives it, and how to get it deleted