Paperboy for OpenClaw
Let your OpenClaw assistant run the weekly SEO loop: read your queries, write and fact check an article, then wait for your OK.
Set up
You will add paperboy as a streamable-http server under mcp.servers and send your key in an Authorization header.
Create a key in Paperboy Settings and add it to ~/.openclaw/.env as PAPERBOY_API_KEY. The OpenClaw docs recommend that global .env file for keys.
Open the Control UI and go to Settings > MCP. Under Configured servers, select Add server.
Give it the name paperboy, pick the Streamable HTTP transport, enter https://paperboyseo.com/mcp, then select Add server.
Headers are not part of that basic dialog. The docs say to use the scoped config editor further down the same page, so add the headers block from the JSON above to the paperboy entry, then choose Save & Publish.
Run openclaw mcp doctor paperboy --probe to confirm OpenClaw can connect and list the tools.
Ask your agent to use Paperboy. The tools run under your normal OpenClaw tool policy.
PAPERBOY_API_KEY=pb_live_YOUR_KEYReplace 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 openclaw mcp doctor paperboy --probe. It validates the saved definition, opens a live connection and reports the tools the server advertises, so you should see the eight Paperboy tools. openclaw mcp status --verbose gives a config-only summary without connecting.
How to remove it
Run openclaw mcp unset paperboy, or use the server row in Settings > MCP to disable or remove the definition.
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.
“List my Paperboy sites, pull the search queries where I rank on page two, and suggest three article topics from them.”
Uses get_sitesget_queriessuggest_topics
“Write an article on the best of those topics and send me the fact-check verdict and sources. Do not publish it yet.”
Uses write_articleget_article
“How did my site perform this month in Search Console? Show clicks and impressions and the queries that moved most.”
Uses get_sitesget_performanceget_queries
Why
OpenClaw is an assistant you run on your own hardware, and it takes remote MCP servers through an mcp.servers map with a headers object. You do not need ClawHub or a skill for this. A plain server entry is enough.
Mind the Gateway. The saved-server commands refuse to run while the local Gateway owns the state directory, so stop it first or edit live in the Control UI. Policy matters too: openclaw mcp tools paperboy with --exclude publish_article keeps the agent from publishing on its own.
Compare
Same engine, two ways in. Pick the one that fits how you already work.
| Feature | Dashboard | OpenClaw | Source |
|---|---|---|---|
| Where you work | paperboyseo.com/app: sites, calendar, fact checks | Open-source AI assistant on your own hardware, in your chat apps | OpenClaw docs: Connect MCP serversRead Oct 29, 2026 |
| How it connects | Sign in and paste your site address. The first article is free. | Remote MCP. OpenClaw connects to remote Streamable HTTP MCP servers (transport: streamable-http) and accepts a headers map, so a bearer key works. | OpenClaw docs: Connect MCP serversRead 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 OpenClaw 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 saved-server CLI commands (add, set, configure, tools, unset) and probe, doctor --probe, login and logout refuse to run while the local Gateway owns the state directory. Stop the Gateway first, or make live edits in the Control UI.
Keep the key out of the config file. Header values are redacted in logs and in openclaw mcp show, and openclaw mcp doctor warns when a header holds a literal token. A reference such as Bearer ${PAPERBOY_API_KEY} does not trigger that warning once the variable is set. A missing variable stays visible as ${PAPERBOY_API_KEY} and logs a warning.
Paperboy tools go through the same tool-profile and tool-policy controls as everything else. To stop the agent publishing, run openclaw mcp tools paperboy --exclude 'publish_article'. Do not set auth: "oauth" on this entry, because static Authorization headers are ignored while OAuth is enabled.
FAQ
Server definitions live under mcp.servers in the OpenClaw config file. The default path is ~/.openclaw/openclaw.json, and OPENCLAW_CONFIG_PATH overrides it.
Saved-server changes need exclusive ownership of the state directory, so the CLI refuses while a Gateway holds it. Stop the Gateway and retry, or edit the server in the Control UI at Settings > MCP.
No. ClawHub is the public registry for OpenClaw skills and plugins, installed with commands such as openclaw skills install. Paperboy connects as a plain MCP server.
Yes. Use a tool filter, for example openclaw mcp tools paperboy --exclude 'publish_article', or set toolFilter.exclude on the server entry. Include and exclude entries accept raw MCP tool names.
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 OpenClaw 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).