Mmcp.market

Revenueos MCP server

by unempyd·io.github.unempyd/revenueos·v0.2.4
No reviews yet

Self-hosted revenue department: find opportunities, execute approved work, measure results.

C57/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C57/100

full report

Adoption
Growing

7 stars936 downloads/wk

Reviews

Write one

Nobody has reviewed Revenueos yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Revenueos tools (13, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • revenueos_ads_audit

    RevenueOS Ads Auditor: ingest an ad platform export and flag wasted spend, over-pacing campaigns and dangerous spend concentration. `csv_path` must be the 13-column claude-ads generic export format (date, account_id, account_name, campaign_id, campaign_name, campaign_status, creative_id, creative_name, conversion_action, conversions, budget, spend, currency); `platform` is one of google, meta, you

  • revenueos_approve

    Approve a pending action from revenueos_today so it can be executed. Approving alone never sends, publishes or spends anything — call revenueos_execute afterwards to act.

  • revenueos_discover_leads

    RevenueOS Lead Discovery: read prospects from OpenOutreach (when installed, across a process boundary) and any CSV drop already in data/exports/, then run the qualification gate. Pass `csv_path` (Instantly/Smartlead columns: email, first_name, last_name, company, title, website, linkedin_url, reason) to import one more file first — it is copied into data/exports/leads-<timestamp>.csv. Only a QUALI

  • revenueos_draft_followups

    RevenueOS Sales Follow-up: draft first-touch cold emails for newly discovered prospects from the business's own canon (offer, differentiators, pain points). Drafts are queued as follow_up actions and are never sent by this tool — call revenueos_approve then revenueos_execute to send one. Set REVENUEOS_DRY_RUN=1 (the Community default) to write sends to data/outputs/ instead of over real SMTP.

  • revenueos_executewrite action

    Execute an approved action: send the drafted email, or run the matching SKILL.md (SEO fix, ads recommendation, content deliverable) against the business context. This is the only tool in RevenueOS Community that sends, publishes or writes a deliverable, and it only acts on actions already approved with revenueos_approve.

  • revenueos_ignore

    Dismiss a pending action from revenueos_today without acting on it.

  • revenueos_lessons

    What RevenueOS learned from this business's own measured results: one dated lesson per executed action that was measured (what was attempted, what the evidence showed, what to do differently). Read this before proposing work — the same lessons are injected into every worker prompt. Run `revenueos learn` (or the CLI) to derive new ones from recent outcomes; nothing here is written by this tool.

  • revenueos_measure

    RevenueOS Revenue Monitor: check every executed action for a measurable result — an SEO re-crawl, a reply or bounce on a sent email, the next ad export's spend delta, or a written content deliverable — and record it. Outcomes are honest: pending until evidence exists, never fabricated.

  • revenueos_results

    What RevenueOS Community has done and what measurable result occurred: every executed action with its outcome (emails sent, replies, SEO fixes confirmed by re-crawl, ad spend deltas, deliverables written). Outcomes are honest — pending until real evidence exists.

  • revenueos_runwrite action

    Run one RevenueOS Community worker now and return what it found: discover, outreach, inbox, seo, ads-audit, content, monitor, measure, or "all" to run every worker in order. Workers only analyse and queue actions — they never send, publish or spend.

  • revenueos_search_skills

    RevenueOS Marketing Intelligence: search the unified skill catalogue (SEO, ads, cold email, content, growth — hundreds of vendored playbooks) for a topic and return matching skills with their source and description. Use this to see which skill a content or SEO action would run before approving it, or to find a skill for a task not yet queued.

  • revenueos_seo_audit

    RevenueOS SEO Auditor: crawl the business's website for missing titles/descriptions, thin pages, duplicate titles and a missing sitemap, and compare domain authority against its configured competitors. Pass `website` to audit a different URL for this one run. Each defect is queued as a seo_opportunity action pointing at the SEO skill that fixes it — nothing is changed until you call revenueos_appr

  • revenueos_today

    The RevenueOS Community brief: pending opportunities awaiting a decision, current pipeline value, and the latest metrics for this connected business. Call this first to see what RevenueOS found and what is waiting on approve/execute/ignore.

Public scan report

scanner v0.1.9 · 2026-09-19 · same rubric, same numbers if you re-run it

1 high1 medium
  • Code scan291 source files scanned8/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • highShell command built from a string (injection risk)exec.shell-concat
    revenueos-0.2.4/skills/pipelines/video-clip-pipeline/scored_pipeline.py: … Get video title title_result = subprocess.run( f'yt-dlp --get-title "{args.url}"', shell=…
  • mediumsubprocess with shell=Trueexec.shell-true
    revenueos-0.2.4/skills/pipelines/video-clip-pipeline/scored_pipeline.py: …y: result = subprocess.run(cmd, shell=True, capture_output=True, text=True, check=…
Overall 57/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Revenueos repository's README, as published. We do not edit it. Read it on GitHub

RevenueOS

A revenue department for one business. It reads your website, ads, leads and mailbox, turns what it finds into a short list of actions, does the ones you approve, and measures what changed.

Connect once. Everything runs free. Pay when you agree with the result.

Free forever to run by hand, including the web panel. Running continuously on a schedule is $99/month, and only after it has measured a result you agreed with, plus 14 days.

Start Pro · Pricing · Talk to a human (or email hello@revenueos.com.au)

Runtime proof · Architecture · Security &amp; approval · Integrations · Community vs Hosted · Capabilities

What it does

  1. Connect once. Give it your website. It fills in the rest and labels every guess.
  2. Discover. It reads the site, the ad exports or ad accounts, the lead lists and the mailbox, and writes what it finds as actions.
  3. Approve. Nothing changes until you approve an action.
  4. Execute. It deploys the site fix, pauses the wasting campaign, sends the email, books the call, raises the invoice, publishes the post.
  5. Measure. It re-reads the live account and records before → after next to the action.
  6. Pay. Nothing is charged until it has measured a result you agreed with.

Try it on your site in one command

uvx revenueos demo https://yoursite.com     # nothing to install; or: pip install revenueos && revenueos demo …

No account, and nothing is kept: the demo builds a workspace in a temporary directory and deletes it before it exits. It is not offline, though. The pages it reads go to whichever model you have configured, and only --no-llm keeps the run entirely local. Here is the whole output on a neutral domain, verbatim:

RevenueOS demo — Example Domain (https://example.com)

  1 pages crawled · ad/analytics tags: none · booking link: no · phones: none seen

  1. MISSING DESCRIPTION — https://example.com
     Page has no meta description.
     → RevenueOS writes the fix as a deliverable you approve, then re-checks the page.
  2. THIN PAGE — https://example.com
     Only ~127 characters of body text were extracted.
     → RevenueOS writes the fix as a deliverable you approve, then re-checks the page.
  3. NO SITEMAP — https://example.com
     No sitemap.xml was discovered at the host root or under the site path.
     → RevenueOS writes the fix as a deliverable you approve, then re-checks the page.
  4. NO CANONICAL — https://example.com
     The homepage declares no canonical URL.
     → RevenueOS deploys this fix itself once the site is connected (git or WordPress), then re-checks it.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreD → Cscore 57: Shell command built from a string (injection risk); subprocess with shell=True

Install directly

claude mcp add revenueos -- uvx revenueos
Add to Cursor

Revenueos: common questions

Is Revenueos MCP server safe?
With care: it is graded C, so read the findings first (57/100). Read the Revenueos safety report
How do I install Revenueos?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Revenueos need an API key?
Yes. The registry entry asks for ANTHROPIC_API_KEY.
Is Revenueos maintained?
The last commit was 7 days ago (2026-09-14). The latest release is v0.2.4.
What can I use instead of Revenueos?
Servers from other publishers that do the same job: build123d MCP server.

Alternatives to Revenueos

Same job from other publishers: the closest match first, then the best rated.

  • build123d MCP
    AI-driven 3D CAD via build123d: execute, render, measure, and export geometry interactively.
    A

More from unempyd →