Paperboy for Claude Code
Ask Claude Code for your page-two queries, then have it write the article, fact check it and save the Markdown into your repo.
Set up
You will register Paperboy as a remote HTTP MCP server named paperboy and pass your API key in an Authorization header.
In Paperboy, open Settings and create an API key. It starts with pb_live_.
In a terminal, run the claude mcp add command above. The default scope is local, so the server loads only in the project where you ran it. Add --scope user to load it in every project.
Start claude and type /mcp to open the MCP panel.
Check that paperboy is listed as connected, with its tool count next to it.
Ask Claude to use a Paperboy tool, for example: list my sites with get_sites.
claude mcp add --transport http paperboy https://paperboyseo.com/mcp \
--header "Authorization: Bearer pb_live_YOUR_KEY"Replace pb_live_YOUR_KEY with a key from Settings, API keys, and never commit it. The MCP docs list every client we cover.
How to tell it worked
Run claude mcp list and look for a Connected status next to paperboy. Run claude mcp get paperboy for details, or type /mcp inside Claude Code.
How to remove it
Run claude mcp remove paperboy. To keep the config but stop the connection, toggle the server off in the /mcp panel.
What you get
Eight tools, the same engine as the dashboard. Reads are free. A pack is $20 for 100 credits; see how credits work.
get_sitesLists your sites with plan, publishing method and whether Search Console is connected. Every other call starts from a site id.
suggest_topicsReturns the next articles to write, each with the search data that is the reason for it.
write_articleStarts a fact-checked article and returns an id at once. The run takes a few minutes. It does not publish unless you pass publish: true.
get_articleReturns the article's status, its fact-check verdict and every source. Poll it after write_article until it reads published or needs_review.
check_claimsFact checks any public URL or pasted Markdown and returns each cited claim with the sources it was compared against.
publish_articlePublishes an article that passed the fact check to the site's publishing target. It changes the live site, so the agent should ask first.
get_performanceSearch Console clicks, impressions and average position for a site, by day and by article.
get_queriesThe queries a site, or one article, appears for in Search Console. This is where page-two keywords show up.
Try it
Plain requests. The tools each one uses are listed under it.
“Use Paperboy to find my page-two queries, pick the best one, and write an article for it.”
Uses get_sitesget_queriessuggest_topicswrite_article
“Get the latest Paperboy article with get_article, save it as a markdown file under content/blog matching our frontmatter, then run check_claims and show me anything it flags.”
Uses get_articlecheck_claims
“Pull get_performance for the last 28 days, then use suggest_topics to propose three articles for the pages that are slipping.”
Uses get_performancesuggest_topics
Why
Claude Code already sits in the repo where your blog lives. With Paperboy attached, one session can read your Search Console queries, ask for a topic, start the article and commit the Markdown next to the code that renders it. Nothing leaves the terminal.
The fact check is the reason to route the writing through Paperboy and not ask the model directly. Every cited claim is compared with the saved text of its source, and the verdict comes back in the same session. An article takes a few minutes, and Claude Code moves a tool call that runs past two minutes into a background task, so you can keep working while it finishes.
Compare
Same engine, two ways in. Pick the one that fits how you already work.
| Feature | Dashboard | Claude Code | Source |
|---|---|---|---|
| Where you work | paperboyseo.com/app: sites, calendar, fact checks | Agentic coding tool that reads your codebase, edits files, runs commands. | Claude Code docs: Connect Claude Code to tools via MCPRead Oct 29, 2026 |
| How it connects | Sign in and paste your site address. The first article is free. | Remote MCP. Claude Code connects to remote HTTP MCP servers and sends custom headers with the --header flag or a headers object. | Claude Code docs: Connect Claude Code to tools via MCPRead Oct 29, 2026 |
| Does it publish without asking? | Your choice: autopilot, or approve each article by email. | No. write_article defaults to publish: false, and the tool descriptions tell the agent to ask first. | MCP docsPaperboy docs |
| Fact check | Every number and cited sentence is compared with the saved text of its source. An article that fails gets one rewrite, then is held for you. | The same engine and the same check. The verdict comes back to the agent: verified, or held with the reason. | How the check worksPaperboy docs |
| What it costs | Plans from $49 a month per site. The first article is free, no card. | Credits: 12 per article, 1 per topic suggestion, 2 per fact check. $20 buys 100. | CreditsPaperboy docs |
| Search Console | Optional read-only Search Console connection. It picks topics from your impressions and reports clicks per article. | get_performance and get_queries return the same read-only data, by day, by article and by query. | Security and dataPaperboy docs |
Facts about Claude Code come from the pages linked in the Source column, read on the date shown. Tools change their docs, so confirm there if a step does not match.
Honest notes
Quirks of this client that can cost you an afternoon.
Scope decides where the key lives. Local scope (the default) and user scope both write to ~/.claude.json. Project scope (--scope project) writes .mcp.json in the project root, and Claude Code asks for your approval before using servers from that file. If you commit .mcp.json, use ${PAPERBOY_API_KEY} instead of the literal key.
A rejected key shows up as a failed connection. If you set an Authorization header and the server answers 401 or 403, Claude Code reports Failed to connect and does not fall back to OAuth. Check the key, and check for a trailing newline, which Claude Code warns about in claude mcp list and /mcp.
Any MCP tool call in the main conversation that is still running after two minutes moves to a background task. The result arrives as a task notification, and you can watch or stop it in /tasks.
FAQ
Run claude mcp add --transport http paperboy https://paperboyseo.com/mcp --header "Authorization: Bearer pb_live_YOUR_KEY". Claude Code writes the server to local scope unless you pass --scope user or --scope project.
Local and user scope are stored in ~/.claude.json. Project scope is stored in .mcp.json in the project root, which you can commit. In .mcp.json you can write Bearer ${PAPERBOY_API_KEY} so the key stays in your environment.
When you configure an Authorization header and the server rejects it with a 401 or 403, Claude Code reports a failed connection instead of starting OAuth. Make sure the key is current and was pasted without hidden whitespace.
Yes. In interactive sessions Claude Code asks for approval before using project-scoped servers from .mcp.json. Run claude mcp reset-project-choices to clear those approval choices.
The tools that read cost nothing. Suggesting topics costs 1 credit, writing a fact-checked article costs 12 credits (refunded if the run fails) and a fact check on its own costs 2 credits. A pack is $20 for 100 credits.
Only if you let it. write_article defaults to publish: false, so a finished article waits for a human, and the tool descriptions tell the agent to ask before publishing. You can also give the agent a read-only key.
Sources
Everything about Claude Code comes from the pages below, read on Oct 29, 2026. Tools change their docs, so check there if a step does not match. If we got something wrong, write to hello@paperboyseo.com.
Keep going
Add the MCP server, ask for a topic, and read the fact check before anything goes live.
claude mcp add --transport http paperboy https://paperboyseo.com/mcp --header "Authorization: Bearer pb_live_..."npx @paperboyseo/cli coming soonPrefer the dashboard? Write my first article free. Prefer to run it yourself? Self-host it (repo coming soon).