> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Assistants connect to Parse over MCP at [https://agent.parse.gl/mcp](https://agent.parse.gl/mcp) (Streamable HTTP). With no sign-in it answers from Parse's public view (the numbers parse.gl's public pages show, up to 5 rows a list), starting with `check_brand`. Signed in with Parse, or sent a workspace key (`parse_mcp_…`), it works in the person's workspace, starting with `get_brief`. Scripts call the same tools over REST at `https://agent.parse.gl/v1/tools/<tool>`.
>
> ```bash
> npx parse-gl init
> ```
>
> To install just the skills: `npx skills add Parsegl/skills`.
> Every tool is also a POST to https://agent.parse.gl/v1/tools/<tool>; its OpenAPI description is https://agent.parse.gl/openapi.json.

# Export rows as a file

> export: a workspace tool on Parse for agents (agent.parse.gl). Arguments, price, and a call over REST and MCP.

Save up to 20,000 rows from search\_answers, search\_cited\_pages, query\_metrics, or list\_work as ndjson or csv (needs first top-up and a scoped filter except list\_work). Returns download URL (24h expiry, requires key) plus exp\_ id for paging via read\_item; files ≤3,000 tokens return inline. Inside own brands, their markets, and tracked items: free (1M rows/mo). Outside scope: 10k rows/day and 50k/mo free, then \$0.01/row within monthly budget (else quoted); identical outside exports within the UTC hour deduplicate.

## Who may call it, and what it costs

| Name | Access | Effect |
| - | - | - |
| `export` | A workspace key, or a sign-in that allows changes. | Spends credits, within the budget |

**Price.** Rows inside the workspace's own scope: free, up to 1,000,000 a month. Rows outside it: \$0.01 a row past the free ones. A public answer older than 90 days costs \$0.001 the first time the workspace counts or lists it, and is the workspace's after, shown in `meta.costCredits`. `quote: true` prices it only and starts nothing. Every reply says what the call cost in `meta.costCredits`. The prices are on [Spending, tracking and stopping](/docs/credits.md).

## Arguments

**tool** `one of search_answers, search_cited_pages, query_metrics, list_work` *required*

search\_answers, search\_cited\_pages, query\_metrics or list\_work: the tool whose rows to export

**args** `object` *required*

that tool's arguments, as you would call it (rows: "mentions" or "comparisons", by: \["question\_group"] included); limit is ignored, cursor continues an earlier export

**format** `one of ndjson, csv` *required*

ndjson: one JSON row a line; csv: one column per value, a share as number columns (\<name>, \<name>\_low, \<name>\_high)

**maxRows** `integer`

at most this many rows in the file; without it the file holds every row the args return (up to the file's cap), and a quote counts them min 1, max 20000

**quote** `boolean`

true: the price and the scope case, writing nothing

Every argument the tool takes, as `GET /v1/tools` serves it, every shared object written out; `https://agent.parse.gl/openapi.json` serves the same schema with the filter and the window named once under `components` and pointed to by `$ref`. MCP `tools/list` leaves out the arguments few calls send, and says the filter and the window once, under `search_answers`; `resolve_ids {"kinds": ["argument"]}` lists what it left out, and a call with any of them runs:

```json theme={null}
{
  "type": "object",
  "properties": {
    "tool": {
      "type": "string",
      "enum": [
        "search_answers",
        "search_cited_pages",
        "query_metrics",
        "list_work"
      ],
      "description": "search_answers, search_cited_pages, query_metrics or list_work: the tool whose rows to export"
    },
    "args": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "that tool's arguments, as you would call it (rows: \"mentions\" or \"comparisons\", by: [\"question_group\"] included); limit is ignored, cursor continues an earlier export"
    },
    "format": {
      "type": "string",
      "enum": [
        "ndjson",
        "csv"
      ],
      "description": "ndjson: one JSON row a line; csv: one column per value, a share as number columns (<name>, <name>_low, <name>_high)"
    },
    "maxRows": {
      "description": "at most this many rows in the file; without it the file holds every row the args return (up to the file's cap), and a quote counts them",
      "type": "integer",
      "minimum": 1,
      "maximum": 20000
    },
    "quote": {
      "description": "true: the price and the scope case, writing nothing",
      "type": "boolean"
    }
  },
  "required": [
    "tool",
    "args",
    "format"
  ],
  "additionalProperties": false
}
```

## Example call

Write a search's rows to a file. Over REST:

```bash theme={null}
export PARSE_API_KEY="<your-key>"

curl -s -X POST https://agent.parse.gl/v1/tools/export \
  -H 'content-type: application/json' \
  -H "Authorization: Bearer $PARSE_API_KEY" \
  -d '{"tool":"search_answers","args":{"filter":{"brand":["brd_21e2e46d-5498-46bc-bd54-791c1acd74e7"],"market":["mkt_6956b477-23eb-43da-99ad-c3e612482b08"]},"window":{"last":"90d"}},"format":"csv","maxRows":5000}'
```

Over MCP, the assistant calls the tool by name with the same arguments:

```json theme={null}
{
  "method": "tools/call",
  "params": {
    "name": "export",
    "arguments": {
      "tool": "search_answers",
      "args": {
        "filter": {
          "brand": [
            "brd_21e2e46d-5498-46bc-bd54-791c1acd74e7"
          ],
          "market": [
            "mkt_6956b477-23eb-43da-99ad-c3e612482b08"
          ]
        },
        "window": {
          "last": "90d"
        }
      },
      "format": "csv",
      "maxRows": 5000
    }
  }
}
```

More calls:

* Say what the export would cost, and write nothing: `{"tool":"search_answers","args":{"filter":{"brand":["brd_21e2e46d-5498-46bc-bd54-791c1acd74e7"]}},"format":"ndjson","quote":true}`

The reply has `data`, `context`, `next`, `page` and `meta`; follow `next` for the calls that come after. A refused call returns `{ code, message, fix }`: see the [error table](/docs/mcp-reference.md#errors).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.