Publication Cadence Tracker MCP server

Publication Cadence Tracker MCP Server

MCP server for the Mamba Labs Publication Cadence Tracker actor on Apify.

Give it a company domain. It tells your agent how much long-form work that company publishes per month, and whether that rate is rising or falling.

Tool

trackpublicationcadence

Returns a flat row per domain: postslast30d, postslast90d, postslast12m, avgpostspermonth, cadencetrend (accelerating, steady, declining, dormant, unknown), trendpctchange, mostrecentpostdate, dayssincelastpost, publicationurl, formatsdetected[], distinctauthorscount, discovery_method, confidence, and an evidence[] array of quotable strings.

Why the trend and not the count

Four pieces a month is unremarkable. Going from four to twelve in six months is a content operation outgrowing its staff. The comparison is stated rather than implied: the last 90 days against the prior 275 days, both normalized to posts per month, with accelerating and declining set at 25 percent either way.

This is editorial output volume, not changelog monitoring. A release feed is detected and rejected rather than counted as published work.

The number it refuses to give you

Publication dates come from the post pages, never from sitemap lastmod. Across 100 measured URL pairs, lastmod tracked the page's own dateModified and ran later than datePublished by a median of 151 to 1653 days on four of six sites. A cadence built on it would report a company that refreshed 200 old posts as a company that published 200 posts.

A page field can fail the same way, so it is checked against its own distribution and against the site's feed. When it fails, datesourcereliable comes back false and every count is nulled. Check that field before quoting a number.

Measured on nine live domains: a rate recovered on 5 of 6 publishers, 3 of 3 controls correctly returning nothing. The one miss is the guard refusing a site whose date field tracks edits.

trackpublicationcadence

What it actually measures

Not whether a company has a blog. How much it published, when, and whether the rate moved.

Finding the blog is most of the work, and it is where a naive version fails. The blog often lives on a different host from the apex and the apex sitemap never mentions it (blog.hubspot.com). A homepage sometimes advertises only a changelog feed while linking to the real blog repeatedly (about.gitlab.com). Paths are often locale prefixed, so /en-uk/ and /bg-bg/ fragment the archive into forty pieces. All three are handled, and publicationurl reports a locale-prefixed section as https://example.com//knowledge/.

Shortened. The full README is on GitHub.