G2 Reviews MCP server

How an agent would call it

Two steps: search returns refs, then data_fetch opens one of them. The arguments below are the arguments that were sent.

{
  "tool": "search",
  "arguments": {
    "query": "notion",
    "sources": [
      "g2"
    ],
    "limit": 2,
    "runId": "<from run_begin>"
  }
}

{
  "tool": "data_fetch",
  "arguments": {
    "sourceId": "g2",
    "ref": "<the ref object the search returned, verbatim — the review travels inside it>",
    "runId": "<from run_begin>"
  }
}

This runs against an account — send Authorization: Bearer <token> with the call. Get one at app.bedrocktap.com/dashboard/tokens; the free tier needs no card, and it reaches g2 like every other source.

What it costs. 3 credits per review row returned; a fetch costs nothing, because the row already carries the review. The search above returned 2 rows and cost 6 credits.

What came back

{
  "ref": {
    "id": "notion-review-13438663",
    "url": "https://www.g2.com/products/notion/reviews/notion-review-13438663",
    "title": "Highly Customizable, Template-Friendly Pages with Easy Hyperlinks"
  },
  "text": "Highly Customizable, Template-Friendly Pages with Easy Hyperlinks",
  "fetchedAt": "2026-09-12T15:01:32.831Z"
}

Both rows carried rating and author in their meta — 4 stars from a "Verified User in Information Technology and Services", and 3.5 from a "Verified User in Computer Software". Reviewers on this platform are frequently anonymised to their industry rather than named. The fetch composed its payload from the row it already held and dispatched nothing.

Observed 2026-09-12. One call against a live source — ask again tomorrow and the rows move.

What a row contains

One row is one review: the review id, its permalink, and the review’s own title. meta carries the star rating and the reviewer, and — where the review states them — the reviewer’s company size, the review date, and the pros and cons as separate fields. The query is a product slug or a G2 review URL, never free text: there is no search-by-name step, so a sentence returns nothing. There is no per-review endpoint here, so `data_fetch` takes the whole ref object the search returned — the review lives in its `meta`. An id on its own carries no review and is refused.

A question it answers. What do enterprise buyers say they dislike about this product, in their own words?

Routing guidance

What an agent reads to decide whether g2 is the right source, and what to reach for when it is not.

Answers

Buyer pain language and feature gaps in business tools. Reviewer role and job title come through — the authority signal no other review source here gives you.

Query shape

A product slug or a full product URL, not a free-text product name. A wrong slug returns nothing.

Price

Priced in credits, per row, per query or per call depending on the source. Every call is quoted before it runs — `cost_estimate` returns the exact figure and spends nothing. See /pricing.

Latency

Moderate (~30-90s).

Prefer instead

`software-reviews` only for cross-platform coverage or the platforms it alone reaches — it costs several times more per row. Prefer the `get_reviews` tool over a raw `search` here: it normalises every review platform into one schema and applies star and date filters this source lacks natively.

Cannot answer

Consumer products (use `trustpilot`), mobile apps (use `app-store-reviews`), or star and date filtering at source — that is applied downstream.

Related sources