mcp

gl.parse/mcpVersion 1.1.0

How ChatGPT and Google AI Mode name, recommend and cite brands.

Status

Responds370 msNov 14, 2026, 14:31 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:31 UTC
Latency: 370 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://agent.parse.gl/mcpResponds370 msNov 14, 2026, 14:31 UTC

No sign-in

Claude Code

claude mcp add --transport http parse https://agent.parse.gl/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: parse
Remote MCP server URL: https://agent.parse.gl/mcp

Cursor

{
  "mcpServers": {
    "parse": {
      "url": "https://agent.parse.gl/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"parse","type":"http","url":"https://agent.parse.gl/mcp"}'

Streamable HTTP

npm: @parse-gl/mcp 1.1.0

Package only

npm (npx)

claude mcp add parse -- npx -y @parse-gl/mcp@1.1.0

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

7 tools

Tools of mcp
	Description		Read-only	Idempotent	Open world
`check_brand`First question about one brand: how often AI mentions it and who is picked instead. Takes the brand's website (best), its name or a brd_ id, and answers in one call. For a brand Parse knows well: its share named and recommended in each of its markets, the brands named most in the market where it is strongest, and the topic it loses on. For one it knows little or nothing about: that fact, and the step that measures it. For a name several companies share: the list to put to the person, with nothing read until they pick. data.kind says which (measured, thin, unplaced, which, unseen). Finding the brand is free; a measured brand's standing is one or two query_metrics reads, free: with credits every row; without, samples and aggregates (own brands in full).	First question about one brand: how often AI mentions it and who is picked instead. Takes the brand's website (best), its name or a brd_ id, and answers in one call. For a brand Parse knows well: its share named and recommended in each of its markets, the brands named most in the market where it is strongest, and the topic it loses on. For one it knows little or nothing about: that fact, and the step that measures it. For a name several companies share: the list to put to the person, with nothing read until they pick. data.kind says which (measured, thin, unplaced, which, unseen). Finding the brand is free; a measured brand's standing is one or two query_metrics reads, free: with credits every row; without, samples and aggregates (own brands in full).	No	Yes	Yes	No
`get_brief`Needs a free Parse sign-in, which this call asks the person for: the person's own brand's brief (what changed, what to do next) and their work record. Call it only when the person wants their own brand, tracking or their record, or says yes to an offer; for any public question use check_brand and the other tools.	Needs a free Parse sign-in, which this call asks the person for: the person's own brand's brief (what changed, what to do next) and their work record. Call it only when the person wants their own brand, tracking or their record, or says yes to an offer; for any public question use check_brand and the other tools.	No	No	No	No
`list_facets`The fields you can filter (filter.facet) and group by (by: facet:<key>): each judgment's definition, values, source, judges, measured quality (labels by Claude annotators, not humans) with its tier, and coverage in your scope over the last 28 days (on the counted engines); the engine facet lists every AI surface with its class and data in your scope; plus this workspace's custom cf_ facets from apply_rubric, query_metrics' measures with their definitions, and how agent numbers relate to the dashboard's. measuresOfImportance documents search_reach, retrieved_by, engine_reach and memory_gap: what each is, the calls that read it, and the evidence behind it with the date measured. Free.	The fields you can filter (filter.facet) and group by (by: facet:<key>): each judgment's definition, values, source, judges, measured quality (labels by Claude annotators, not humans) with its tier, and coverage in your scope over the last 28 days (on the counted engines); the engine facet lists every AI surface with its class and data in your scope; plus this workspace's custom cf_ facets from apply_rubric, query_metrics' measures with their definitions, and how agent numbers relate to the dashboard's. measuresOfImportance documents search_reach, retrieved_by, engine_reach and memory_gap: what each is, the calls that read it, and the evidence behind it with the date measured. Free.	No	Yes	Yes	No
`query_metrics`Count, share, trend: answers, share named / recommended / first, position, tone and treatment mix, citations, pages and sites cited, comparisons won and lost (one brand: subject), search_reach (a brand's sites in retrieved result lists; no by), memory_gap (a brand named with search on against search off, on the questions both answered; no by) and concentration (answers naming the top 1, 3, 5 brands; no by; list_facets has each measure's evidence). Group by brand, topic, market, question, engine, surface_class, day, week, month, site, page, page_type, axis, versus_brand; by brand takes answers, shares, position, tone and treatment, not citations or comparisons (those take a subject). brands: [ids] lists just those brands. Numbers cover the counted engines unless filter.engine or filter.surfaceClass says otherwise, or by names engine or surface_class (context.surfaces says which). Every cell has its answers, questions and a 95% range; compare: prior adds the matched change and significance; by week or month gives the matched trend. Free: with credits every row; without, samples and aggregates (own brands in full).	Count, share, trend: answers, share named / recommended / first, position, tone and treatment mix, citations, pages and sites cited, comparisons won and lost (one brand: subject), search_reach (a brand's sites in retrieved result lists; no by), memory_gap (a brand named with search on against search off, on the questions both answered; no by) and concentration (answers naming the top 1, 3, 5 brands; no by; list_facets has each measure's evidence). Group by brand, topic, market, question, engine, surface_class, day, week, month, site, page, page_type, axis, versus_brand; by brand takes answers, shares, position, tone and treatment, not citations or comparisons (those take a subject). brands: [ids] lists just those brands. Numbers cover the counted engines unless filter.engine or filter.surfaceClass says otherwise, or by names engine or surface_class (context.surfaces says which). Every cell has its answers, questions and a 95% range; compare: prior adds the matched change and significance; by week or month gives the matched trend. Free: with credits every row; without, samples and aggregates (own brands in full).	No	Yes	Yes	No
`resolve_ids`Turn brand names, domains, URLs, topic, market or place names ("Austin, TX"), or question wordings into Parse's typed ids (brd_, top_, mkt_, plc_, qst_, pg_, site:), up to 25 at once. Each match says why it matched, its score, and whether you track it; brands say whether Parse has enough on them (indexed, thin, new, not_indexed), their company, the answers naming the brand itself, and whether it is local, with its locations and area; places their level and parent; questions what data they have. When several companies carry the name, the result's ambiguous lists them. A brand's locations come from public data only (Parse's own read of the brand's site and listings, and a place this workspace set): a franchise's or chain's own list of locations cannot be given to Parse, and a brand with none shows none. Free.	Turn brand names, domains, URLs, topic, market or place names ("Austin, TX"), or question wordings into Parse's typed ids (brd_, top_, mkt_, plc_, qst_, pg_, site:), up to 25 at once. Each match says why it matched, its score, and whether you track it; brands say whether Parse has enough on them (indexed, thin, new, not_indexed), their company, the answers naming the brand itself, and whether it is local, with its locations and area; places their level and parent; questions what data they have. When several companies carry the name, the result's ambiguous lists them. A brand's locations come from public data only (Parse's own read of the brand's site and listings, and a place this workspace set): a franchise's or chain's own list of locations cannot be given to Parse, and a brand with none shows none. Free.	No	Yes	Yes	No
`search_answers`Search AI answers by brand (named, recommended, first, not named, warned), topic, market, question, engine, place the question is about (plc_ ids) or country asked from, site or page cited, keywords or phrases (filter.text), or any facet from list_facets. Compact rows with ids; open them with read_answers. view: "diff" shows which brands and cited pages came and went for up to five questions or one topic, by 28-day step. Rows marked shared are answers a workspace shares: evidence to read, counted in no other workspace's metrics. Free: with credits every row; without, samples and aggregates (own brands in full).	Search AI answers by brand (named, recommended, first, not named, warned), topic, market, question, engine, place the question is about (plc_ ids) or country asked from, site or page cited, keywords or phrases (filter.text), or any facet from list_facets. Compact rows with ids; open them with read_answers. view: "diff" shows which brands and cited pages came and went for up to five questions or one topic, by 28-day step. Rows marked shared are answers a workspace shares: evidence to read, counted in no other workspace's metrics. Free: with credits every row; without, samples and aggregates (own brands in full).	No	Yes	Yes	No
`search_cited_pages`Pages AI answers cite, by brand, topic, market, question, engine, site or facet. For outreach pass pages = third_party: most cited pages are brands' own sites, and this leaves them out. Each row: citations, answers and questions citing it (over the whole filter), weeks cited, answersCiting, answersNaming and answersOmitting (over every answer citing it, the brand rule aside: not the same answers as the first counts), page type (the judge's) and kind (the one to read), owner, brands listed, and whether it lists the brand (listsBrand, with listsBrandBy: the page judge, or the name absent from the stored page), and retrievedBy: how many search surfaces returned it for those questions. brandRule: "not_named" lists gap pages. Reading here records the ask for the page judge when a page was never judged or names a brand it has not judged. Free: with credits every row; without, samples and aggregates (own brands in full).	Pages AI answers cite, by brand, topic, market, question, engine, site or facet. For outreach pass pages = third_party: most cited pages are brands' own sites, and this leaves them out. Each row: citations, answers and questions citing it (over the whole filter), weeks cited, answersCiting, answersNaming and answersOmitting (over every answer citing it, the brand rule aside: not the same answers as the first counts), page type (the judge's) and kind (the one to read), owner, brands listed, and whether it lists the brand (listsBrand, with listsBrandBy: the page judge, or the name absent from the stored page), and retrievedBy: how many search surfaces returned it for those questions. brandRule: "not_named" lists gap pages. Reading here records the ask for the page judge when a page was never judged or names a brand it has not judged. Free: with credits every row; without, samples and aggregates (own brands in full).	No	Yes	Yes	No

Details

Registry status: Active
Published: Nov 12, 2026
Updated: Nov 12, 2026
Website: https://parse.gl/docs/mcp⁠ (opens in a new tab)
Repository: https://github.com/Parsegl/parse⁠ (opens in a new tab)
Categories (suggested): Data and analytics Marketing and SEOSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing