Paperboy for n8n
Attach Paperboy to an n8n AI Agent node, or call its REST API from an HTTP Request node, and run the article loop on a schedule.
Set up
You will add an MCP Client Tool node to an AI Agent in your workflow and point it at Paperboy with a Bearer Auth credential.
Open your workflow and add an AI Agent node. Click the Tool + connector on it and search for MCP Client Tool.
Set Endpoint to https://paperboyseo.com/mcp and set Server Transport to HTTP Streamable.
Set Authentication to Bearer Auth, create a new credential, and paste pb_live_YOUR_KEY as the Bearer Token. (A Header Auth credential with Name Authorization and Value Bearer pb_live_YOUR_KEY works the same way.)
Leave Tools to Include on All, or choose Selected or All Except to control which Paperboy tools the agent can see.
Connect a chat model to the AI Agent, then run the workflow with a prompt that asks for one of the Paperboy tools.
Node: MCP Client Tool (attach it to an AI Agent node)
Endpoint: https://paperboyseo.com/mcp
Server Transport: HTTP Streamable
Authentication: Bearer Auth
Bearer Token (in the new Bearer Auth credential): pb_live_YOUR_KEY
Tools to Include: AllReplace 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
Set Tools to Include to Selected and open the tool picker: it should list the eight Paperboy tools. Then ask the agent to list your Paperboy sites and check that the execution shows a get_sites tool call.
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.
“Every Monday, list my Paperboy sites, pull last week's top queries for the first one, and post the five queries closest to page one in Slack. Then suggest three new article topics.”
Uses get_sitesget_queriessuggest_topics
“When a new topic is added to my content calendar sheet, write the article on my main site, wait for it to finish, then email me the link and the fact-check verdict.”
Uses get_siteswrite_articleget_article
“Take the draft URL from the chat message, fact check it with Paperboy, and reply with every claim that has no supporting source.”
Uses check_claims
Why
n8n gives you two doors. The MCP Client Tool node works only when it is attached to an AI Agent. For a plain workflow step with no agent, use the separate MCP Client node. Either way, pick HTTP Streamable and a Bearer Auth credential.
The docs page for the tool node still labels its field SSE Endpoint, though current node versions default to HTTP Streamable, which n8n's own source confirms. The Tools to Include setting has an All Except option, and that is how you hide write_article and publish_article from an agent that should only read.
Compare
Same engine, two ways in. Pick the one that fits how you already work.
| Feature | Dashboard | n8n | Source |
|---|---|---|---|
| Where you work | paperboyseo.com/app: sites, calendar, fact checks | Workflow automation platform with built-in AI agent and MCP nodes | n8n docs: MCP Client Tool nodeRead Oct 29, 2026 |
| How it connects | Sign in and paste your site address. The first article is free. | Remote MCP. The MCP Client Tool node lets an AI Agent call tools on a remote MCP server, with Bearer, Header, multiple headers or OAuth2 authentication. | n8n docs: MCP Client Tool nodeRead 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 n8n 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.
The MCP Client Tool node is a sub-node that only works attached to an AI Agent. To call a Paperboy tool as a plain workflow step with no agent, use the separate MCP Client node instead (it has a Tool field and a Manual or JSON Input Mode).
The docs page for the MCP Client Tool node still shows a single SSE Endpoint field. In n8n's own source, node versions 1.2 and later show Endpoint plus Server Transport with HTTP Streamable as the default and Server Sent Events marked Deprecated. Paperboy needs HTTP Streamable.
Tools to Include has All, Selected and All Except. Use All Except to hide write_article and publish_article from an agent that only needs to read, because Paperboy's OpenAPI lists 12 credits for each article.
FAQ
Use the MCP Client Tool node attached to an AI Agent, so the agent can pick Paperboy tools on its own. If you want to call one fixed tool as a normal workflow step, use the MCP Client node.
Either works. n8n's docs describe bearer auth as header auth with the Name set to Authorization and the Value set to Bearer followed by the token, so a Bearer Auth credential only needs the key itself.
Yes. Add an HTTP Request node, choose Import cURL on its Parameters tab, and paste a curl command with the Authorization: Bearer header. The base URL is https://paperboyseo.com/api/v1.
Yes. Add a Webhook node set to POST, copy its Production URL, publish the workflow, and give that URL to Paperboy as the webhook destination. The Test URL only listens after you select Listen for test event.
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 n8n 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).