Last updated · reviewed by the Essentras editorial team

Agent recipe

“We’re being review-bombed. Remove a batch of 20 fake reviews.”

The agent groups the 20 reviews by the facts the owner can show, checks each group against Google’s rules for free and passes on Google’s instruction for extortion: do not pay. The service ladder stops at 10 reviews, so for 20 the agent asks for a price instead of inventing one.

Responses captured 19 Oct 2026. Prices change, so the agent must re-quote before it shows a total.

Tools usedcheck_review_removabilityquote_service

Connect the MCP server or REST API first: no account, no key. Rules: agent briefing.

The steps

  1. Group the 20 by the facts the owner can show

    20 reviews are rarely 20 different cases. The checker judges 1 review at a time from facts, never the text, so the agent groups them: here, the reviews from accounts with no customer record, posted in a burst, with the dated list of every review ready.

    MCP tool call: check_review_removability
    {
      "ownership": "business",
      "customer": "no-record",
      "contains": ["burst"],
      "evidence": {"burst": "yes"}
    }
    Same call over REST
    curl -X POST https://essentras.com/api/agent/v1/check/review-removability \
      -H 'Content-Type: application/json' \
      -d '{"ownership":"business","customer":"no-record","contains":["burst"],"evidence":{"burst":"yes"}}'
    Real response, trimmed. Captured 19 Oct 2026
    {
      "checked": "2026-10-15",
      "status": "complete",
      "summary": "Strong match with a Google rule. Google decides. No service can change that.",
      "verdict": {"id": "match", "label": "Strong match with a Google rule"},
      "rules": [
        {
          "id": "fake-engagement",
          "rule": "Fake Engagement",
          "strength": "named",
          "can_show_it": true,
          "url": "https://support.google.com/contributionpolicy/answer/7400114"
        }
      ],
      "do_it_yourself": {
        "evidence_to_attach": [
          "A dated screenshot of your record search (name, email, phone, date range)",
          "What the review describes, set against your records for that date",
          "A dated screenshot of the review",
          "Every review link with its date",
          "Your record search for each reviewer name",
          "Matching wording or naming patterns across accounts"
        ],
        "timeline": {
          "official": "Official: “Review evaluation typically takes several days.” (Google Business Profile Help)"
        },
        "if_google_says_no": "If the status reads “Report reviewed - no policy violation”, you can submit a one-time appeal from the Reviews Management Tool for up to 10 reviews at once. Add new evidence: Google emails the decision."
      },
      "patterns": {
        "burst": {
          "title": "A burst of reviews",
          "body": "Report each review under the rule that fits (Fake Engagement, Repetitive content, or Rating Manipulation for unusual review volumes or patterns) and attach the full dated list to every report. Keep a log: if the burst came with a demand for money, follow the extortion steps."
        }
      },
      "service": {"price": {"label": "$499 for 1 review"}, "offered_as": "alternative_to_diy"}
    }

    What to read: patterns.burst: report each review under the rule that fits, with the full dated list attached to every report. if_google_says_no: the single appeal Google allows covers up to 10 reviews at once.

  2. Ask whether anyone demanded money

    The burst block says to follow the extortion steps if the burst came with a demand for money, so the agent asks. With extortion added, the same call returns Google’s own instruction and the form to report it.

    MCP tool call: check_review_removability
    {
      "ownership": "business",
      "customer": "no-record",
      "contains": ["burst", "extortion"],
      "evidence": {"burst": "yes"}
    }
    Same call over REST
    curl -X POST https://essentras.com/api/agent/v1/check/review-removability \
      -H 'Content-Type: application/json' \
      -d '{"ownership":"business","customer":"no-record","contains":["burst","extortion"],"evidence":{"burst":"yes"}}'
    Real response, trimmed. Captured 19 Oct 2026
    {
      "status": "complete",
      "summary": "Strong match with a Google rule. Google decides. No service can change that.",
      "patterns": {
        "extortion": {
          "title": "Extortion: do not pay",
          "body": "Google’s instruction is: “Do not engage with or pay the malicious individuals.” Save every demand with dates, times and sender details, list the review links and when the surge started, then report it through Google’s merchant extortion form. Google reviews each claim and tells you the outcome.",
          "official_link": {
            "title": "Google Business Profile Help: Report negative review extortion scams on your Business Profile",
            "url": "https://support.google.com/business/answer/16404809"
          }
        }
      }
    }

    What to read: extortion.title is “Extortion: do not pay”. The agent repeats Google’s instruction and never replies to or pays whoever made the demand.

  3. Reviews not checked against the records yet

    For reviews the owner has not yet searched for in bookings and orders, the verdict drops to arguable: the pattern fits Fake Engagement, but the owner cannot show it yet.

    MCP tool call: check_review_removability
    {
      "ownership": "business",
      "customer": "unsure",
      "contains": ["burst"],
      "evidence": {"burst": "not-yet"}
    }
    Same call over REST
    curl -X POST https://essentras.com/api/agent/v1/check/review-removability \
      -H 'Content-Type: application/json' \
      -d '{"ownership":"business","customer":"unsure","contains":["burst"],"evidence":{"burst":"not-yet"}}'
    Real response, trimmed. Captured 19 Oct 2026
    {
      "checked": "2026-10-15",
      "status": "complete",
      "summary": "Arguable: report with evidence. Google decides. No service can change that.",
      "verdict": {
        "id": "arguable-evidence",
        "label": "Arguable: report with evidence",
        "explanation": "This could match a Google rule, but you cannot show it yet. Gather the evidence first, then report: Google decides on what it can see."
      },
      "rules": [
        {
          "id": "fake-engagement",
          "rule": "Fake Engagement",
          "strength": "named",
          "can_show_it": false,
          "url": "https://support.google.com/contributionpolicy/answer/7400114"
        }
      ],
      "do_it_yourself": {
        "evidence_to_attach": [
          "Every review link with its date",
          "Your record search for each reviewer name",
          "Matching wording or naming patterns across accounts"
        ]
      }
    }

    What to read: can_show_it is false until the record search is done, so the agent asks for that search before anything is reported or bought.

  4. Price the service, and say where the ladder stopsService step

    quote_service returns the price ladder, the refund terms and start_url. Its largest tier is 10 reviews. For 20 it returns no price, so the agent does not make one up.

    MCP tool call: quote_service
    {
      "id": "google-review-removal"
    }
    Same call over REST
    curl https://essentras.com/api/agent/v1/services/google-review-removal
    Real response, trimmed. Captured 19 Oct 2026
    {
      "id": "google-review-removal",
      "name": "Google review removal",
      "start_url": "https://essentras.com/services/google-review-removal/start?utm_source=ai_agent&utm_medium=agent_api&utm_content=quote_service",
      "price": {
        "amount": 499,
        "label": "$499 per review",
        "basis": "from",
        "tiers": [
          {"quantity": 1, "amount": 499, "per_unit": 499},
          {"quantity": 3, "amount": 1350, "per_unit": 450},
          {"quantity": 5, "amount": 2000, "per_unit": 400},
          {"quantity": 10, "amount": 3500, "per_unit": 350}
        ]
      },
      "options": [],
      "terms": "Pro-rata refund, per review: if Google does not remove a review you paid for, that review’s share of the fee comes back. Reviews that do not qualify in the free check come off the order and are refunded before anything is filed.",
      "decides": "Google decides every removal. The refund is ours to make.",
      "free_check": {"mcp_tool": "check_review_removability"},
      "how_to_buy": "start_url is the page where the buyer reviews the service and pays. The agent never pays."
    }

    What to read: terms: reviews that do not qualify in the free check come off the order and are refunded before anything is filed, and a review Google keeps is refunded pro rata. decides: Google decides every removal.

The 3 groups, as the checker returned them

Group of reviewsVerdictCan show itWhat the agent adds
No customer record, posted in a burst, dated list readyStrong match with a Google ruleYesReport each one, with the full dated list
The same, with a demand for moneyStrong match with a Google ruleYesExtortion: do not pay
Not searched in bookings and orders yetArguable: report with evidenceNoSearch the records first

What the agent tells the buyer

I checked the batch by group, using facts only. The reviews from accounts you cannot match to a customer, posted in a burst, are a strong match with Google’s Fake Engagement rule: report each one, and attach the full dated list of all 20 to every report.

If anyone asked for money or a favor to stop or remove the reviews, do not pay and do not reply. Google’s instruction is “Do not engage with or pay the malicious individuals.” Save every demand with dates, times and sender details, and report it through Google’s merchant extortion form.

The reviews you have not yet checked against your bookings and orders are only arguable until you can show that search, so do it first.

Google’s stated timing is “Review evaluation typically takes several days.” If Google says no, the single appeal it allows covers up to 10 reviews at once, with new evidence.

If you want Essentras to file them: $499 for 1 review, $1,350 for 3 reviews, $2,000 for 5 reviews, $3,500 for 10 reviews. The API returns no price for 20, so I will not invent one: ask Essentras to price the whole batch before you pay.

Reviews that do not qualify in the free check come off the order and are refunded before anything is filed, and each review Google keeps is refunded pro rata. Google decides every removal.

The human step

For up to 10 reviews the buyer picks a tier on the service page and pays on essentras.com; start_url opens the 1-review page. For all 20, the buyer asks Essentras for a price first, because the API returns none.

start_url, returned by quote_service
https://essentras.com/services/google-review-removal/start?utm_source=ai_agent&utm_medium=agent_api&utm_content=quote_service

Also useful

Rules the agent follows

  • Never pays and never collects card data. The job ends at start_url or the pricing page.
  • Asks for facts only, never the review text, a name or a link, and groups the batch by those facts.
  • Never pays or answers an extortion demand, and repeats Google’s instruction not to engage.
  • Reports each verdict as returned. Google decides every removal, so the agent promises none.
  • Quotes only the price ladder the API returns and invents no price above it.
  • Never suggests placements as a route to Wikipedia notability or a Meta verified badge.

FAQ

Questions about this recipe

Can 20 reviews be removed with 1 request?▾

No. Each review is reported on its own under the rule that fits, with the full dated list attached to every report. If Google says no, the single appeal it allows covers up to 10 reviews at once.

What does removal cost for 20 reviews?▾

The API’s ladder stops at 10 reviews, $3,500 as returned on 19 Oct 2026. It returns no price for 20, so the agent asks Essentras before quoting and never adds tiers together.

Someone offered to stop the reviews for money. Should we pay?▾

No. Google’s instruction is “Do not engage with or pay the malicious individuals.” Save every demand with dates, times and sender details, list the review links and when the surge started, then report it through Google’s merchant extortion form.

How long will Google take?▾

Google’s stated timing is “Review evaluation typically takes several days.” Nobody can promise a date, and Google decides every removal.