Who may call it, and what it costs
Price. Free over the last 90 days. 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. A call whose window reaches further back counts one even sample of its answers, the deepest whose past answers, owned or not, are worth at most 25% of the month’s budget in effect, at most $5, bought when called with no quote (history: "auto"); history: "all" counts every answer within the month’s budget, and history: "free" reads the last 90 days only and says what each sample would cost. Every reply says what the call cost in meta.costCredits. The prices are on Spending, tracking and stopping.
Arguments
pages (default): pages AI answers cite; result_lists: search APIs’ ranked lists (filter takes question, engine, site, page); result_list_diff: for one question on one surface, pages that entered and left its list
default named; not_recommended keeps judged answers recommending none of the filter brands; warned filters to answers flagged with facet mention.advised_against
Industry or category markets. For countries use country, and for cities use place. up to 50
surface ids (resolve_ids with kinds: [“surface”] lists them); without engine or surfaceClass, the counted engines up to 10
classes of engines to cover; default counted up to 5
plc_ ids (resolve_ids finds them): the place a question is about, with the places under each (a region holds its cities). “all”: every place, in place of a local subject’s area. A country code here reads as filter.country for one release
ISO country codes the question was asked from; an answer asked with no place set counts as US up to 20
Full-text search over answer text: keywords, “exact phrases”, AND/OR/NOT, NEAR/n, prefix*. A call reads at most the first 100,000 matches (20,000 in search_answers) before the brand filter and the rest apply: a brand filter does not narrow it, so a common word over a long window can miss a brand’s answers; narrow by window, topic, market or engine
default all: public plus this workspace’s own; own: only the answers this workspace bought; tracked: its own answers and those about the questions, topics and brands it watches with the track tool (not the brands it added in the app); public: public answers only; index: the answers parse.gl’s public pages count, which a logged-out call always reads
answers past 90 days, $0.001 each once: auto (default) a sample worth up to a quarter of the month’s budget, at most $5; all, every answer within the budget; free, none, with each sample’s cost
all, or third_party: only pages on no brand’s own site (not the filter brand’s, not any other brand’s) and not Parse’s own. For a listing pitch, also pass filter.brand and listsBrand: false. Write the value bare, with no quotes inside the string. Default all
needs filter.brand: true keeps pages the page judge says list the brand; false, pages that do not: by the judge, or a stored copy that never names it. With brandRule not_named, false is the pages to pitch and true the pages that list you while answers omit you
how brands count: company (default; a company and its products are one brand) or product (each brand on its own, so a product’s numbers leave out its siblings)
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:
Example call
Find pages AI cites in a market, other than the brands’ own, in answers that leave your brand out. Over REST:- Only the pages the page judge says do not list the brand: the pages to pitch:
{"pages":"third_party","filter":{"brand":["<brd_ id>"],"brandRule":"not_named"},"listsBrand":false} - Which pages a search API retrieved for a question gained and lost:
{"view":"result_list_diff","filter":{"question":["qst_…"],"engine":["tavily"]}}
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.