Minds: Synthetic Market Research Panels vs Firecrawl MCP Server

M

create_panel

Creates a new research Panel from existing Groups or inline Group configurations when the intended outcome is a new Panel. Follow-up research on an existing Panel does not require creation. Composite creation is atomic and rolls back partial Group failures. Panels are private by default; enabling link sharing also publishes the attached Groups and Minds.

ask_panel

Submits one respondent-visible question to an existing Panel and starts asynchronous responses from its Minds. Follow-up questions remain within the existing Panel; this operation does not create or enumerate Panels. The full question value may reach respondents and is not planner-only metadata. Scale, categorical, and qualitative questions are classified automatically, and the response includes status and workspace links.

export_panel

Starts an asynchronous export of Panel results and returns an export job ID. Supports executive briefs, full reports, and raw data in PDF, HTML, PNG ZIP, DOCX, PPTX, Markdown, CSV, XLS, or SPSS SAV formats, subject to report-kind compatibility.

export_mind

Generates a branded profile for one existing Mind, identified by exact ID or fuzzy name. Markdown is returned inline by default; PDF, DOCX, and PPTX artifacts are returned as base64 with a workspace link.

export_group

Export a group brief through the same unified branded renderer used by the web app. Supports Markdown, PDF, DOCX, and PPTX. Binary artifacts are returned as base64.

export_heatmap

Export a completed website heatmap from a panel message, identified by the message ID that the panel reports on its completed results. Returns the same ZIP archive as the web app, including its unified-renderer PDF report, Markdown, images, and metadata.

list_panels

Lists the authenticated user's Panels with their Groups, Minds, status, sharing state, and workspace or shared links. Accepts an optional fuzzy name search. Panels may also be described as studies, surveys, research projects, focus groups, or research conversations.

get_panel_status

Returns current Panel state, live progress for in-flight questions, completed per-Group results, linked Minds, Panel links, and the status of a specific asynchronous export job when export identifiers are supplied.

list_groups

Lists the authenticated user's Groups, including member Minds, sharing state, and workspace or shared links. Accepts an optional fuzzy name search. Groups may also be described as audiences, segments, cohorts, target groups, or persona collections.

create_group_from_brief

Creates a grounded Group of synthetic Minds from a population or audience brief. It can combine authoritative web research, supplied sources, research files, and reviewed spreadsheet distributions; persists provenance and allocation audits; supports balanced, segment-coverage, and benchmark-depth sizing; is idempotent for identical inputs; and keeps the Group private unless link sharing is enabled.

ask_group

Submits one respondent-visible question to a single existing Group. The Group may be identified by exact ID or fuzzy name. The operation creates a private one-Group Panel, starts asynchronous responses from its Minds, and returns the Panel identifier and links for status retrieval.

plan_panel_study

Creates or revises a non-executing draft for a multi-question or structured Panel study. The draft records intent, respondent-visible stimulus and questions, response formats, locale, method, outputs, confirmation questions, and revision metadata. It does not start research.

firecrawl_scrape

Retrieve and extract content from one supplied URL through Firecrawl. Use this when the request identifies a page and needs its content or defined fields. It can return markdown, HTML, links, screenshots, branding data, a targeted answer, or JSON matching a supplied schema; JSON is useful when the requested result has defined fields, while markdown preserves readable page content. This tool operates on a known page. For a set of pages use `firecrawl_crawl`, and to discover page URLs use `firecrawl_map` or `firecrawl_search`. Options include JavaScript render delay, cache age, main-content filtering, PII redaction, and lockdown cache-only retrieval. Browser actions may change the live page when interactive actions are enabled. Firecrawl may reuse recently indexed content instead of refetching the page, and the reuse window varies by domain. Set `maxAge: 0` to force a live fetch, or a smaller `maxAge` to bound how stale reused content may be. A successful response does not by itself confirm that the state it describes is still current. Returns the selected content formats and page metadata.

firecrawl_map

Enumerate URLs indexed under one website through Firecrawl without fetching each page's content. Use this when the request asks for a site's URL inventory, when several relevant pages must be located, or when the desired page URL is unknown. An optional `search` term narrows the URL list, while sitemap, subdomain, query-parameter, and result-limit options control coverage. Returns matching URLs rather than page bodies. Retrieve one page with `firecrawl_scrape`; collect content across multiple pages with `firecrawl_crawl`.

firecrawl_search

Search web, news, or image sources and return ranked results. Operators include quoted phrases, `-term`, `site:host`, `inurl:term`, `intitle:term`, and `related:host`; the set is non-exhaustive. `includeDomains` and `excludeDomains` are mutually exclusive hostname filters; categories limit results to GitHub, research, PDF, or developer sources. For a programming question, add `categories: ["developer"]`. It searches an index of GitHub issues, merged pull requests, repository READMEs, and curated documentation sites, and returns the hits in `data.developer` beside the web results. `categories: ["research"]` restricts these web results to research-affiliated websites and returns page snippets. The `firecrawl_research_*` tools are a separate surface that searches paper abstracts and full text across biomedical (PubMed, bioRxiv, medRxiv) and arXiv literature. `scrapeOptions` can attach extracted page content; pages fetched this way use a fixed reuse window and ignore `maxAge`, so use `firecrawl_scrape` when a live fetch is required. Returns source-type result groups and usage metadata. Authenticated responses can include an `id` for optional search feedback.