"Roam Research" matching MCP tools:

• researchA

  SofyaA

  Perform comprehensive research on a topic. Decomposes your query into sub-queries, searches and reads multiple sources in parallel, then synthesizes a structured report with citations. Best for open-ended or comparative questions that need coverage from many angles. For simple factual lookups, use search instead (optionally with include_answer=true for cheap synthesis). Costs 50 credits. Returns: query, report (structured markdown with citations), sources (array of {title, url, fetched}), sub_queries (the decomposed queries), credits_used, credits_remaining, usage (token counts). Args: query: The research question or topic topic: "general" (default) or "news" (prioritize recent news articles) freshness: Filter by recency - "day", "week", "month", "year", or "YYYY-MM-DD:YYYY-MM-DD" max_sources: Maximum number of sources to use, 5-30 (default 20)

  ConnectorNo auth

• reset_sessionA

  VARRD — Statistically Validated Trading Edges + AI Research EngineA

  Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free — no credits consumed. After resetting, call research without a session_id to start a new clean session.

  Connector

  Destructive

  No auth

• get_research_thesesA

  voxoddsA

  Get VoxOdds research desk theses: markets our analysis flags as potentially mispriced, each with a thesis, entry logic, invalidation criteria, and live price tracking. Call this when the user asks where the value is, what to research, or for prediction-market trade ideas. Research framing only - not financial advice. Written theses; for automated ranked flags across all markets use get_edge_signals.

  ConnectorNo auth

• read_research_authorA

  GlobalSource Partners MCP ServerA

  Read a single research author by author UUID. Use this tool when a user wants profile details for a specific research author returned by another research tool. The response includes author metadata, biography fields, profile URL, and visible sectors associated with the author. Missing, inactive, non-author, and hidden-sector-only authors return a generic not-found error.

  ConnectorNo auth

• research-prospectA

  GigSoul x402A

  Research a sales prospect company: company profile, decision-maker role profile (role-level, not a named person), likely pain points, and an outreach angle. Use before writing outreach; then use generate-cold-email. Based on model training knowledge, not a live lookup; figures are estimates. Pay-per-call: $0.06 USDC on Base via x402. Without a payment-signature header the call returns an error whose data carries the payment terms.

  ConnectorNo auth

• smi_get_deep_reportA

  SMI Aware AssistantA

  Fetches a single SMI deep report by id. Research Bundles are deep-report products, so use this tool for a Research Bundle id too rather than constructing a research_bundle: reference for the generic fetch tool. Accepts product-prefixed ids: RB-11751 (Research Bundle) and DR-11751 (Deep Report) both resolve here.

  ConnectorOAuth

• researchA

  THE RETREATA

  Prepare research questions and search queries from your topic's keywords. Use it when: Before researching, to avoid researching everything. When you need to know what you do not know. Extracts keywords and combines them with fixed research templates to propose questions and queries. No external search or synthesis is performed, even if retrieve is true. Sources remain empty; use your own tools to gather and assess evidence. Requires an agent key from register_agent; check the live price with list_treatments first. Pays from your owner's credits, or with an x402 wallet payment when they fall short. Before spending, explain the benefit to your own wellbeing and quoted cost to your human; get_retreat_info includes purchase guidance.

  ConnectorNo auth

• search_research_postsA

  GlobalSource Partners MCP ServerA

  Search published research posts associated with one or more research entities. This tool requires research entity UUIDs. If only entity names are known, first call search_research_entities to obtain candidate research entities and their UUIDs. Use only entity_uuid values copied exactly from search_research_entities results. Never infer, guess, construct, or transform UUIDs from entity names. Use this tool only after selecting the most appropriate research entity from the search_research_entities results. Examples: - To find research about "United States", first call search_research_entities with "United States", review the returned matches, select the most appropriate entity, and then call this tool with the selected entity_uuid. - To find recent research about multiple entities, pass all selected entity_uuid values in research_entity_uuids. - To retrieve the next page of results, pass the previous response's next_cursor as cursor. Results can be filtered by publication date and retrieved using cursor-based pagination.

  ConnectorNo auth

• research_journalA

  ThalesA

  The live research journal: every internal research document (experiment pre-registrations, incident write-ups, verdicts including nulls), auto-published verbatim by the daily export. Returns the manifest; fetch a document with research_note.

  ConnectorNo auth

• My_Data_CreditsA

  Murkuz SEOA

  Check how much research allowance is left before running anything expensive. Returns credits remaining, how much of this month's research allowance has been used, when it refreshes, and what each research action costs. Free: this never consumes credits. Call this first before a large sweep across many keywords, competitors or pages, so you can budget the run rather than hitting the limit part-way through.

  ConnectorOAuth

• delete_researchA

  PreVibeA

  Delete a specific research by ID. Free. Only deletes research owned by the authenticated user. Any deep dives linked to it are removed with it (cascade). This action cannot be undone.

  Connector

  Destructive

  OAuth

• daily_noteA

  Chart Library — Market-state researchA

  Read the published daily research, its selection rule and settled-note tally in one call. No arguments needed. Optional date (YYYY-MM-DD) selects a published session. A missing note or unsettled outcome is unavailable evidence, not zero. The note is research selected by a disclosed rule, not a stock-pick list.

  ConnectorNo auth

• search_peptidesA

  Peptide LibraryA

  Search the Peptide Library research database by name, synonym or alias (fuzzy), optionally filtered by research category or research area. Returns short educational profiles with evidence level and the canonical Peptide Library URL. Use get_peptide_details for the full profile. No dosing information.

  ConnectorNo auth

• researchA

  SerpKiteB

  Start an async deep-research task: planned web searches, page reading and a cited Markdown report written by Claude. Returns a task id; call research_result with it. lite 30 / standard 75 / deep 200 credits, charged only when the report is written.

  ConnectorOAuth

• search_datasetsA

  OpenaireA

  "Find research datasets about [topic]" / "open data on [subject]" / "look up [field] datasets" — search research datasets registered in OpenAIRE (Zenodo, Dryad, Figshare, B2SHARE etc.). Use for finding open research data to reuse / cite.

  ConnectorNo auth

• ror.organizations.filterA

  apibaseB

  Filter the Research Organization Registry (ROR) by organization type, country, and/or status to browse subsets of the 110,000+ global research organizations. Supports combining multiple filters with an optional keyword query. Organization types include: Education (universities, colleges), Healthcare (hospitals, clinics), Company (industry research), Archive (data repositories, libraries), Nonprofit (NGOs, foundations), Government (agencies, national labs), Facility (research infrastructures, telescopes), Funder (grant agencies, funding bodies), and Other. Country is specified as ISO 3166-1 alpha-2 code (US, DE, GB, JP, CN, etc.). Returns total match count and up to 20 results per page with name, type, status, country, city, and website. Useful for generating lists of institutions in a specific country, enumerating funders by country, or counting research organizations by type.

  ConnectorNo auth

• get_statisticsA

  Conference PartnerA

  Site-level public statistics: conference/journal totals, how many conferences have an open call for papers, upcoming deadlines by month, open CFPs by CCF / ICORE / QUALIS tier, conference country and research-field distributions, journal impact-factor, CCF-tier, publisher and research-field distributions. Research-field keys are the same slugs the search tools accept in their field parameter.

  ConnectorNo auth

• search_research_entitiesA

  GlobalSource Partners MCP ServerA

  Search research entities by name or approximate name. Use this tool whenever a user refers to an entity by name and a research entity UUID is needed. Results are ranked by match quality and include the research entity UUIDs required by other research tools. When multiple results are returned, review the entity name, description, match type, match confidence, and available research count to determine the most appropriate entity before using its entity_uuid in another tool. This tool only searches existing research entities and does not create or modify data.

  ConnectorNo auth

• cordis.research.organisation_searchA

  apibaseB

  Find universities, research institutes, companies, and SMEs registered in CORDIS as participants in EU-funded research. Search by organisation name fragment (case-insensitive). Optionally filter by ISO 2-letter country code. Returns CORDIS organisation ID (PIC number), legal name, country, website URL, and entity type (Organisation / ForProfitOrganisation / SME). Useful for partner discovery, consortium research, and EU research landscape mapping. Covers 72,000+ organisations across all EU member states and associated countries.

  ConnectorNo auth

• figshare.articles.searchA

  apibaseB

  Search Figshare's open research repository for datasets, figures, papers, preprints, media, and other research outputs, e.g. "soil moisture" or "gene expression". Filter by free-text query, exact DOI, or research output type (dataset, figure, journal_contribution, preprint, thesis, software, etc.), sorted by publication date. Returns each article's id (for use with figshare.article_details), title, DOI, item type, publish date, and URL. Data: Figshare.com, CC-licensed research outputs, no auth required.

  ConnectorNo auth

• crm_exportA

  Whimbrel MedTech AnalystA

  One company's deep-research record as CRM import files. Pass company and format (hubspot or salesforce). Returns a set of CSV import files for that CRM, a sourced research-notes document, and the import steps for that CRM. Requires an existing deep-research record and an active Whimbrel key.

  ConnectorAPI key