Home · Services · Automate link building

Automate execution, not strategy

Searching a site, placing an order, tracking its publication: an agent can do all of that without a human reopening a dashboard twenty times a day. Choosing which page to push, balancing the anchor mix, deciding the pace: that one, no. Here's the line, and why it doesn't move.

See the boundary See the technical reference
✓ API + MCP server✓ Sandbox key to test✓ Daily cap per key
The problem

The manual work eating your days

Placing a link doesn't take long. Everything around it does. Multiplied by twenty or thirty orders a month, that search-and-verify work ends up costing more than the strategy itself.

Finding a relevant site

Finding, on the right topic and in the right language, a site whose profile (traffic, referring domains, price) matches the budget and the page you want to push. Done by hand, that means opening dozens of listings one by one.

Briefing and chasing

Writing or approving the article angle, the anchor, the target page. Then chasing an order that has gone quiet for days.

Tracking every order

Checking back on every order in flight to know where it stands: accepted, being written, published. Without notifications, that means opening the same dashboard every day.

Verifying what went live

Once a link is reported live, opening the article to confirm the anchor and the destination URL match what was ordered, and that the link actually exists.

What automates well

Four tasks that are repetitive and checkable

Exactly the kind of task an agent handles better than a person who has to stop what they're doing several times a day to do them.

01

Querying the catalog

Filter by niche, language, minimum Trust Flow, shelf (Plancton, Corail, Nautilus) or price, and compare dozens of sites in a single call where a manual search opens as many listings.

02

Placing the order

Once a site is picked, the order is created in one call, settled immediately if the prepaid balance covers it. A sandbox key lets you test the whole flow before wiring up a real key, without ever spending a cent.

03

Tracking without polling

A signed webhook subscription notifies every stage (order accepted, published, cancelled) instead of hammering the API in a loop to check if anything changed.

04

Verifying what went live

Once an order is marked published, the article URL is returned directly in the response: an agent can check it automatically, where a human used to open every link by hand.

Why a daily cap

Every API key is capped at roughly twenty orders a day. That's not a hidden limitation, it's a deliberate guardrail: an agent that goes into a loop (a bug, a misread instruction, a retry storm) stays bounded before it can do damage. It's the kind of detail that tells apart a system built for real agents from a web form wearing an API as a costume.

The boundary

Three decisions that stay human

Not out of excessive caution: automating these produces exactly the signal Google penalizes after an algorithm update.

⚠ If automated
Choosing which pages to push

An agent with access only to the catalog of selling sites knows nothing about the target site's structure: its pillar pages, what is actually holding back current rankings, what deserves a link now rather than in two months.

✓ Stays a human call

That choice is made by looking at the site receiving the link, not the catalog of the site selling it. It's a strategic judgment call, not a filter to automate.

⚠ If automated
Balancing the anchor mix

An agent that repeats the same anchor formula on every order builds, without meaning to, a monotone profile: exactly the signal a spam algorithm is best at catching.

✓ Stays a human call

The mix (brand, soft anchors, descriptive, a measured fraction of exact-match) is calibrated by knowing the link profile already in place on the target site, a fact the ordering API never sees.

⚠ If automated
Deciding the pace

Twenty orders placed on the same day because a script ran unbounded look like a purchase spike, not the natural growth of a site gaining authority over time.

✓ Stays a human call

The daily cap per API key bounds the worst case, but the intended spacing over time remains a scheduling decision, not a setting you hand to a loop.

Attention

This topic naturally invites autopilot talk: search and order without thinking about it. In SEO, that's exactly what builds the link profiles that get hit after an algorithm update. What gets automated here is execution, not strategy. For the full method on calibrating a campaign (anchor mix, spacing, budget), see the link-building campaign page.

In practice

How an agent connects

The Nautilinks catalog (sites sorted into three flat-price shelves: Plancton at 5 €, Corail at 15 €, Nautilus at 30 €) is reachable through a REST API and a remote MCP server, no package to install. An MCP client (Claude Code, claude.ai, Cursor…) or a direct HTTP call speak the same data contract.

Payment always follows a human validation: either a prepaid balance a person funded ahead of time, which the agent spends order by order, or, failing that, a Stripe payment link that same person has to open. A sandbox key (sn_test_ prefix) lets you test search, ordering and tracking without ever touching the real balance.

See the full API and MCP reference →

Frequently asked questions

Can an agent automate the entire link-building process, from picking the site to paying for it?

Not all of it, and it shouldn't. An agent can search the catalog, place an order and track its publication without a human stepping in at every stage. Payment always stays validated by a person: either upfront through a prepaid balance already funded, or in the moment through a Stripe link a human has to open. Choosing which pages to push, balancing anchors and setting the publication pace remain strategic decisions that don't delegate to an algorithm.

Why is there a daily order cap?

Because an agent that goes off the rails, a looping bug, a misread instruction, a retry storm, becomes a real risk the moment it has access to a payment method. The cap, on the order of twenty orders a day per key, bounds that risk without getting in the way of normal use. Past that threshold the API answers with 429 and the code daily_order_cap_reached, and a replay with the same idempotency key never counts twice.

Can an agent just pick the anchors on its own?

Technically the API does not stop it. It's still a bad idea. An agent repeating the same anchor formula on every order builds a monotone profile, exactly the kind of signal that triggers a footprint after an algorithm update. The anchor mix is decided by knowing the link profile already in place on the target site, a fact a sales catalog does not contain.

Does this work alongside an existing link-building strategy?

Yes: the automation covers execution (search, order, track, verify), not strategy. Target pages, pace and anchor mix are still set upstream, by hand or with an agency, then executed through the API or the MCP server at the intended rhythm.

Do I need to write code to get started?

Not if you're going through an MCP client (Claude Code, claude.ai, Cursor): the connection is a single API key and a URL, no package to install. Writing code becomes useful to go further, a cron job checking order status, an alert on webhooks, but it isn't a prerequisite to start.

Can I test this before spending a single euro?

Yes. A sandbox key (sn_test_ prefix) simulates the full flow, search, order, tracking, without ever touching the prepaid balance or creating a real order with a publisher.

Two ways to stop losing your days

Wire an agent to the API and keep control of the strategy, or hand the whole thing, execution and strategy, to the agency.

Connect an agent Discover the agency