> ## 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.

# Parse for agents and developers

> Research brands and markets with your agent.

**Parse** (parse.gl) is the AI visibility workspace built for agents. Give Claude, ChatGPT, and Cursor one shared workspace to check your market, draft edits and pitches, and see what changes. Parse (parse.gl) is the AI visibility platform. It is not Parse Platform, the open-source app backend, and not a document-parsing tool.

* **Who it suits:** founders, lean marketing teams and agencies who want to know whether AI recommends their brand, who it recommends instead, and what to do next.
* **Coverage:** ChatGPT and Google AI Mode power the main visibility metrics. Your agent can also ask other supported engines, including Perplexity, and check what search services return. Traffic and sales need separate data.
* **Connect an assistant:** 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>`. [Get started](/docs/get-started.md).

## What an assistant can do alone, and what needs a person

| Step | Who | How |
| - | - | - |
| Read any brand, topic or market | The assistant, alone | `check_brand`, `resolve_ids`, `query_metrics`, `search_answers`, `search_cited_pages` — over MCP or REST with no sign-in, at the free level |
| Sign up and track a brand on Free | A person, once | Sign up at parse.gl with the brand's website. No card. |
| Make a key | A person approves, once | The assistant signs in with Parse; or, for scripts and CI, a key on [Agents](https://parse.gl/app/settings/agents) |
| Read the brief, search, query | The assistant, with the key | `get_brief` first in each session, then each reply's `next` |
| Ask now, run a baseline, fetch live pages, track | The assistant, within the monthly budget the person set | Each runs when called, within the workspace's monthly budget; past it nothing is bought and the assistant asks. Tracking starts when the person asked for it |
| Add credits, raise a cap | A person | Never through an assistant |
| Billing, members, keys, removing a brand | A person, in Parse | Never changed through an assistant |

Your agent can spend workspace credits within the limits you set. A person adds credits, accepts terms and sends outreach.

## Where to go next

> [card] [Get started](/docs/get-started.md)
>
> Add Parse to Claude, ChatGPT, Claude Code, Cursor, Codex or a script: each step, the sign-in screens, and how to tell it worked.

> [card] [Your first session](/docs/first-session.md)
>
> Five things to ask an assistant, the call it makes and what comes back.

> [card] [Spending, tracking and stopping](/docs/credits.md)
>
> Every price, the three limits, how paid calls run, tracking, exports, refusals and how to stop.

> [card] [Reading the numbers](/docs/numbers.md)
>
> What each measure counts, ranges and significance, windows, levels, missing values, and why the app differs.

> [card] [Workflows](/docs/workflows.md)
>
> The loop, site fixes, agencies, research, and what Parse does not do.

> [card] [MCP reference](/docs/mcp-reference.md)
>
> Connect to agent.parse.gl, keys and the free level, a page for every tool, replies, paging, every error code, the CLI.

> [card] [Agencies and local businesses](/docs/agencies.md)
>
> Workspaces for clients, comparing brands, scoped exports, and places: plc\_ ids, local filters and listings.

> [card] [Rates and limits](/docs/limits.md)
>
> Free allowances, the monthly budget, team roles and rate limits.

> [card] [Data and trust](/docs/trust.md)
>
> What Parse collects and stores, what the agent service records, who can read bought answers, retention, deleting a workspace and contacts.

> [card] [Changelog](/docs/changelog.md)
>
> Changes to tools, limits and docs.

## Reading a Parse number

* **In the app and on public pages**, **Recommended** is the share of AI answers inside a market or topic that recommend a brand (as a pick, an alternative, or an option with pricing or specs); **Mentioned in** is the broader detail behind it, and **Brand score** summarizes standing across markets. Every figure is a share of answers, not of buyers, sales or traffic.
* **Through an assistant**, `query_metrics` returns `share_recommended` (Recommended), `share_named` (Mentioned in), and other counts and shares with a 95% range on matched questions. [Reading the numbers](/docs/numbers.md) explains each field.
* “Mentioned in” counts answers from ChatGPT and Google AI Mode. Public index questions are asked in English, with the location set to the United States. Parse asks a tracked brand's own topics from its buyers' country, and a local business's own topics name its place. A local business's market questions are asked in each place of its area, as someone there would ask them, on ChatGPT and Google AI Mode on every plan: its home place on Free, up to 15 places on a paid brand. A brand on Free is asked on ChatGPT each week.
* Public pages count up to the last 180 days and print the window each figure covers. Under 20 answers, a share is weak evidence.
* A brand missing from a page is not proof that AI never mentions it, and a later rise does not prove a task caused it.

The full method for the app and the public pages is on [Methodology](https://parse.gl/metrics). How to cite a number is on [Parse for AI systems](https://parse.gl/ai).

## Machine-readable entry points

* Every docs page, [Pricing](https://parse.gl/pricing.md) and [Parse for AI systems](https://parse.gl/ai.md) as Markdown: add `.md` to the address, or send `Accept: text/markdown`.
* [llms.txt](https://parse.gl/llms.txt), an index of the site, and [llms-full.txt](https://parse.gl/llms-full.txt), every docs page in one file.
* [AI catalog](https://parse.gl/.well-known/ai-catalog.json), which links the MCP server, the skill index and these docs.
* The server's tools as OpenAPI at `https://agent.parse.gl/openapi.json`, its common jobs at `https://agent.parse.gl/guide`, and the command-line client via `npx parse-gl`.
* The Parse, content and outreach skills at [/.well-known/agent-skills/index.json](https://parse.gl/.well-known/agent-skills/index.json).


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