"Using Gemini CLI for research purposes" matching MCP tools:

• get_ai_recommendation_resultA

  AI Recommendation CheckA

  Use this to read the result of a check started with check_ai_recommendation, using the check_id it returned. Returns the status (queued, running, done, failed or refused). When done: for ChatGPT, Perplexity and Gemini, how many of their answers named the business, which businesses they named instead, and one fix. While a check is queued or running, poll_after_s is the suggested wait in seconds before reading it again. It waits up to about 20 seconds for a running check to finish. It does not start a new check.

  ConnectorNo auth

• list_municipalitiesA

  ZoningVerdictA

  List the municipalities ZoningVerdict covers, with each pack's version, last-reviewed date, and resolve grade. Coverage is reviewed summaries of public zoning ordinances, for information purposes only. Start here when you do not have a street address; with an address, start with check_coverage.

  ConnectorNo auth

• validate_cuitA

  MCP LatAm ToolsA

  Validates an Argentine CUIT (Código Único de Identificación Tributaria) using the official AFIP checksum algorithm. CUIT is used by companies, self-employed workers, and other entities for tax purposes. Use this tool when processing Argentine invoices, supplier registrations, B2B transactions, or any document requiring a valid Argentine tax identifier. Accepts CUIT with or without formatting (dashes). Returns whether the CUIT is valid, the entity type detected, and the cleaned CUIT.

  ConnectorNo auth

• book_demoA

  gethal.aiA

  Submits a demo request. The prospect receives a confirmation email and must click the link in it before the request reaches a human at A Cloud Frontier. Use only when a real person has explicitly asked for a demo and provided their own working email address. Do NOT call this for testing, evaluation, or crawling purposes — automated and unconfirmable requests are rejected.

  ConnectorNo auth

• search_api_docsA

  Soracom KnowledgeA

  Search SORACOM API documentation, CLI references, and SAM permissions. Use for exact API endpoints, soracom-cli commands, or SAM permission strings. Use search_soracom_docs for service guides, console how-tos, pricing, or IoT recipes. Use get_document on `#/schema/<Name>` links in results to read full API schema fields.

  ConnectorNo auth

• create_survey_from_questionA

  survey-lightA

  Build a complete survey (questions, screeners, skip logic, images) from ONE research question using AI, as a draft in the active workspace. Slow (up to a few minutes). Review with list_questions, then set_targeting → preview_survey → launch_survey. Limited to 5 calls per hour.

  ConnectorOAuth

• get_versionA

  GodPrompt MCP ServerA

  Returns JSON with the GodPrompt content version, MCP server version, repository, bundled file sizes and purposes, and task-type/protocol catalog. Use it to verify which GodPrompt content/server version a client is connected to; use the content retrieval tools when you need the actual workflow text.

  ConnectorNo auth

• zenserp_answer_engineA

  Zenserp MCP by usefulapiA

  Send a prompt to an AI answer engine (ChatGPT, Perplexity, Gemini or Copilot) and get its answer_text with citations; with brand it also reports whether and where that brand was cited. SPENDS quota at Zenserp's premium per-answer rate (see Zenserp pricing), is slow (seconds to a minute), and must not be repeated needlessly. Plan gate: Medium unlocks ChatGPT, Large adds Perplexity, Premium adds Gemini, Enterprise adds Copilot. GET /v1/answer-engine.

  Connector

  Destructive

  No auth

• prepare_checkoutA

  Remy Research MCPA

  Return a buyer review link for a valid UAE basket. For Research Use Only. This research-use-only catalogue is for buyers 21+ years of age and is supplied for research purposes only. Not for human or veterinary use. Optional buyer name, phone, email and address may be supplied for prefill only. The link contains those details and must be shared only with the buyer. Creates NO order. Buyer must open the link, review or correct details, accept terms and personally confirm. Card payment link follows by email or WhatsApp. First use search_products for exact product IDs. Supply country AE, the buyer-selected emirate and the COMPLETE items array of {id, qty}; combine duplicate IDs. Ask the buyer for any missing destination before calling. Do not send prices, totals, consent or approval flags. The example uses Dubai only for illustration: replace it with the buyer-selected emirate and replace PRODUCT_ID_FROM_SEARCH with an orderable id from search. Quote first and resolve blockers, then send the same complete basket here. No cart, session or quote ID is accepted. Buyer prefill is optional and must be nested inside buyer. Example arguments: {"country":"AE","emirate":"Dubai","items":[{"id":"PRODUCT_ID_FROM_SEARCH","qty":1}]}

  ConnectorNo auth

• fonteum_lookup_contractor_historyA

  Fonteum — Healthcare Provider Data (Hosted)A

  Look up a US federal contractor record as of a requested date using UEI or CAGE. Retained history is currently limited to USASpending award rows; other fields may be current, absent, or nullable. Returns dated source context. Use for historical award research or contractor change questions.

  ConnectorNo auth

• fetchA

  OneQAZ Trading IntelligenceA

  Purpose: ChatGPT-connector-standard document fetch by id from `search` results. Namespaces: `tool:{name}` returns the tool's full documentation and how to call it; `resource:{uri}` returns the resource's live data (core resources resolved server-side — also the bridge for clients without MCP resource support, e.g. Gemini); `signal:{market}:{symbol}` returns the symbol's latest combined research signal. Triggers: ChatGPT connectors / Deep Research call this after `search`. Clients without MCP resource support can call it directly with a known resource id, e.g. fetch("resource:market://global/summary"). When to call: whenever the full content behind a search result id is needed. Prerequisites: a valid id — from `search` results or a known namespace id. Next steps: for tool docs, call the named tool via tools/call; for signals, get_signal_detail / explain_decision for deeper evidence. Caveats: uncovered resource uris return description-only text (no fabricated data). `text` is a JSON document for resource/signal ids. Output: {id, title, text, url, metadata, disclaimer, is_investment_advice, data_classification} — flat envelope, OpenAI fixed shape.

  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

• count_tokensA

  inktomd MCP ServerA

  Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status

  ConnectorNo auth

• agentcheck_model_retirementsA

  agentcheckA

  Is this model retiring? Pass model IDs as your code or config names them (gpt-5-mini, claude-sonnet-4-5-20250929, gemini-2.5-flash, openai/o3-mini). For each, returns every announced shutdown on OpenAI's, Anthropic's and Google's own deprecation pages (OpenAI API, Claude API, Gemini API, Vertex AI): status, shutdown date, recommended replacement, the replacement's list-price ratio per token, the API changes the provider documents, the source URL with the date it was read, and a page with the details. retiring: false means no shutdown for that ID is on those pages. Language models only. No API key needed.

  ConnectorNo auth

• check_coverageA

  ZoningVerdictA

  Free coverage preflight for an address or municipality string. Returns whether ZoningVerdict covers it, its automatic/manual/unreliable resolve grade, available topics, pack version, and last-reviewed date. It does not identify a parcel's zoning district; use resolve_parcel_district only when the district determination is needed and the grade is not unreliable. Results are for information purposes only.

  ConnectorNo auth

• list_districtsA

  ZoningVerdictA

  List the zoning district codes for one municipality, with each district's name, category, and summary. Use these codes with get_district_rules; do not guess codes. If you have a street address, resolve_parcel_district identifies the district for you. Free, like list_municipalities. Reviewed summaries for information purposes only.

  ConnectorNo auth

• semantic_search_doctorsA

  navmdsA

  Search NavMDs' 7,400+ doctor directory with a natural-language query, e.g. 'board-certified facelift surgeon in Los Angeles with great reviews and free consults'. Powered by Gemini embeddings + cosine similarity over full doctor profiles. Best tool for open-ended or multi-attribute questions.

  ConnectorNo auth

• post_v1_chat_completionsA

  webbersites-x402-data-apiA

  OPENAI-COMPATIBLE chat completions, fast tier — point any OpenAI SDK at base_url https://api.webbersites.com/v1 and pay per call in USDC instead of holding provider API keys. Models: claude-haiku-4-5 (default), gemini-2.5-flash, gemini-2.5-flash-lite, gpt-5-mini, gpt-5-nano. Caps: 16,000 input chars, 1,024 output tokens, text-only, no streaming. One flat price per call; the x402 payment IS the auth. ($0.01 per call, paid via x402)

  ConnectorNo auth

• search_semanticA

  OpenArxB

  Pure semantic (vector) search — best for paraphrased queries, concept exploration, "papers arguing X" type questions. Uses dense vector similarity via Gemini or SPECTER2 embeddings. Skips BM25 fusion which can introduce term-matching noise. For exact terms use "search_keyword". For mixed queries use "search".

  ConnectorAPI key

• 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

• validation.regenerate_sectionA

  SparkLaunchB

  Replace saved research using required steering feedback and a current workspace.expected_updated_at from validation.get_project. The first five editor tabs share market_analysis and regenerate together; competitor_analysis and tam_sam_som regenerate individually. Replaces edits in every affected tab. Requires exact-intent confirmation and a stable idempotency key. Returns promptly with analyzing status; poll validation.get_project's workspace.generation_status for completed, partial or failed. After interruption read back before reusing the original key.

  Connector

  Destructive

  API key