Chroma’s official MCP server: vector search and collection management for RAG workflows.
rows.page is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Push CSV, JSON, JSONL or Parquet from your agent and get a link a human can explore.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http rows-page-mcp https://rows.page/mcp
# 2 — ask your agent for something these tools do
# push, pin_finding, get_dataset and 3 more
rows.page costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http rows-page-mcp https://rows.page/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
6 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Publish rows as a rows.page dataset (or a new version of one) and get a shareable URL. Pass exactly one of csv, tsv, jsonl, json, rows or url. Up to 16 MB inline; use url for bigger files. Identical content returns unchanged: true without a new version. Re-pushes report rows_delta, columns_added/removed and a diff_url. Anonymous datasets expire after 7 days unless kept. Finding views use the rows.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| csv | string | no | CSV text with a header row |
| tsv | string | no | TSV text with a header row |
| jsonl | string | no | One JSON object per line |
| json | no | A JSON array of objects (or an object holding one), as text or as a value | |
| rows | array | no | Rows as an array of objects |
| url | string | no | http(s) URL of a CSV, TSV, JSON, JSONL or Parquet file to fetch and publish |
| format | string | no | Format of url when it cannot be told |
| name | string | no | File name, e.g. orders.csv |
| title | string | no | Dataset title shown on the page |
| summary | string | no | A few sentences for the human: what this is and what to look at |
| dataset | string | no | Existing dataset id to push a new version to |
| token | string | no | Dataset token (rpt_...) proving ownership of dataset |
| key | string | no | Stable name for upserts with an API key, e.g. nightly-orders |
| id_column | string | no | Column that identifies a row across versions, for changed-row diffs |
| visibility | string | no | private needs Pro or Max |
| findings | array | no | — |
| source | string | no | Where the data came from (URL or description) |
| run | string | no | Run id of the job that produced it |
| commit | string | no | Commit sha of the code that produced it |
Pin a finding (a saved, titled view) to a dataset you own. Finding views use the rows.page query language in q: word or "two words" searches text columns; field:value, field:"a b", -field:value, field:* (not null), -field:* (null), field:foo* (prefix); field:>20, >=, <, <=, field:10..20, ISO dates (at:>2026-09-01); dot paths for nested JSON (`payload.customer.country:NL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | yes | Dataset id |
| token | string | no | Dataset token (rpt_...) when not using an API key |
| title | string | yes | Short headline of the finding |
| note | string | no | Why it matters, in a sentence or two |
| q | string | no | Filter in the rows.page query language |
| sort | string | no | Sort, e.g. -price,name |
| cols | string | no | Visible columns, e.g. id,price,country |
| sql | string | no | Optional SQL against the table data |
| version | integer | no | Pin to this version instead of the latest |
| row_count | integer | no | Rows matching the view, if you know it |
Read a dataset: meta, recent versions, findings, columns and the first 20 preview rows.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | yes | Dataset id |
| version | integer | no | Version number; latest when omitted |
| token | string | no | Dataset token, needed for private datasets without an API key |
List the datasets kept on your account, newest first. Needs an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cursor | string | no | next_cursor from the previous page |
Delete a dataset you own. Its URL stops working immediately.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | yes | Dataset id |
| token | string | no | Dataset token when not using an API key |
Show your plan, its caps (file size, datasets, version history) and usage.
No parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install rows.page or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish rows.page can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.