> ## 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.

# Resolve names to ids, find by meaning, list facets

> resolve_ids: a tool that also answers without a key on Parse for agents (agent.parse.gl). Arguments, price, and a call over REST and MCP.

Resolve up to 25 brand names, domains, URLs, topics, markets, places ("Austin, TX"), or question wordings to Parse ids (brd\_, top\_, mkt\_, plc\_, qst\_, pg\_, site:), with match score and index status. Use match: "meaning" for semantically nearest questions, topics, or markets to a text or id. Use kinds: \["facet"], \["surface"], \["measure"], or \["argument"] alone for the dictionary of valid filter facets, AI surfaces, metric definitions, or extra tool arguments. Free.

## Who may call it, and what it costs

| Name | Access | Effect |
| - | - | - |
| `resolve_ids` | No key needed over REST, at the free level; a workspace key or sign-in reads in full. | Reads only |

**Price.** Free. Every reply says what the call cost in `meta.costCredits`. The prices are on [Spending, tracking and stopping](/docs/credits.md).

## Arguments

**q** `list of string`

names, domains, URLs, question wordings or typed ids (up to 25); match: "meaning" takes one text or qst\_/top\_/mkt\_ id; the dictionary takes words to look for, or none; kinds argument takes tool names up to 25

**kinds** `list of one of brand, topic, question, market, page, site, place, facet, surface, measure, argument`

what to match: brand, topic, question, market, page, site, place (default all); with match: "meaning" question, topic, market; or facet, surface, measure alone for the dictionary; argument alone, with tool names in q: what a tool takes beyond its tools/list entry up to 7

**match** `one of name, meaning`

name (default): exact names, domains and ids; meaning: nearest in meaning, for a phrase with no exact match or to find what to track next

**unit** `one of brand, answer, mention, evidence, comparison, page, page_brand, question, topic_brand`

dictionary only: facets of this unit (answer, mention, evidence, comparison, page, page\_brand, question, topic\_brand)

**filter** `object`

match: "meaning" only: within these markets or topics

**filter.market** `list of string`

Industry or category markets. For countries use country, and for cities use place. up to 50

**filter.topic** `list of string`

up to 50

**subject** `string`

match: "meaning" only: brd\_ id, adds its share named in each result (90 days)

**excludeTracked** `boolean`

match: "meaning" only: leave out what this workspace tracks

**minSimilarity** `number`

match: "meaning" only: 0.3 to 0.99, default 0.6 min 0.3, max 0.99

**limit** `integer`

match: "meaning" only: default 10 min 1, max 50

**format** `one of compact, full`

compact (≈6k tokens, default) or full (≤20k)

**fields** `list of string`

columns to keep in each row up to 40

**explain** `boolean`

false: leave out the one-sentence note (data.note)

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": {
    "q": {
      "description": "names, domains, URLs, question wordings or typed ids (up to 25); match: \"meaning\" takes one text or qst_/top_/mkt_ id; the dictionary takes words to look for, or none; kinds argument takes tool names",
      "minItems": 1,
      "maxItems": 25,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 500
      }
    },
    "kinds": {
      "description": "what to match: brand, topic, question, market, page, site, place (default all); with match: \"meaning\" question, topic, market; or facet, surface, measure alone for the dictionary; argument alone, with tool names in q: what a tool takes beyond its tools/list entry",
      "maxItems": 7,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "brand",
          "topic",
          "question",
          "market",
          "page",
          "site",
          "place",
          "facet",
          "surface",
          "measure",
          "argument"
        ]
      }
    },
    "match": {
      "description": "name (default): exact names, domains and ids; meaning: nearest in meaning, for a phrase with no exact match or to find what to track next",
      "type": "string",
      "enum": [
        "name",
        "meaning"
      ]
    },
    "unit": {
      "description": "dictionary only: facets of this unit (answer, mention, evidence, comparison, page, page_brand, question, topic_brand)",
      "type": "string",
      "enum": [
        "brand",
        "answer",
        "mention",
        "evidence",
        "comparison",
        "page",
        "page_brand",
        "question",
        "topic_brand"
      ]
    },
    "filter": {
      "description": "match: \"meaning\" only: within these markets or topics",
      "type": "object",
      "properties": {
        "market": {
          "description": "Industry or category markets. For countries use country, and for cities use place.",
          "maxItems": 50,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 3,
            "maxLength": 220
          }
        },
        "topic": {
          "maxItems": 50,
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 3,
            "maxLength": 220
          }
        }
      },
      "additionalProperties": false
    },
    "subject": {
      "description": "match: \"meaning\" only: brd_ id, adds its share named in each result (90 days)",
      "type": "string",
      "minLength": 3,
      "maxLength": 220
    },
    "excludeTracked": {
      "description": "match: \"meaning\" only: leave out what this workspace tracks",
      "type": "boolean"
    },
    "minSimilarity": {
      "description": "match: \"meaning\" only: 0.3 to 0.99, default 0.6",
      "type": "number",
      "minimum": 0.3,
      "maximum": 0.99
    },
    "limit": {
      "description": "match: \"meaning\" only: default 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    },
    "format": {
      "description": "compact (≈6k tokens, default) or full (≤20k)",
      "type": "string",
      "enum": [
        "compact",
        "full"
      ]
    },
    "fields": {
      "description": "columns to keep in each row",
      "maxItems": 40,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 60
      }
    },
    "explain": {
      "description": "false: leave out the one-sentence note (data.note)",
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
```

## Example call

Find a brand by its domain, with its markets and whether Parse has enough on it. Over REST:

```bash theme={null}
curl -s -X POST https://agent.parse.gl/v1/tools/resolve_ids \
  -H 'content-type: application/json' \
  -d '{"q":["notion.so"],"kinds":["brand"]}'
```

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

```json theme={null}
{
  "method": "tools/call",
  "params": {
    "name": "resolve_ids",
    "arguments": {
      "q": [
        "notion.so"
      ],
      "kinds": [
        "brand"
      ]
    }
  }
}
```

More calls:

* Find a place's plc\_ id: `{"q":["Austin, TX"],"kinds":["place"]}`
* Find the questions Parse already asks that mean the same: `{"q":["best project management tool for agencies"],"match":"meaning","kinds":["question"],"limit":5}`
* The dictionary: every field to filter and group by, every AI surface and every measure: `{"kinds":["facet"]}`
* Only the facets of a brand mention: `{"kinds":["facet"],"unit":"mention"}`
* The arguments search\_answers takes beyond those its tools/list entry shows: `{"kinds":["argument"],"q":["search_answers"]}`

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.