Skip to main content
Glama
789,265 tools. Updated 2026-11-16 02:31

"A tool to query data in Metabase and ask questions" matching MCP tools:

  • Search or list stores in the Partle marketplace. Use for store-led questions ("what hardware shops are in Madrid?") rather than product-led ones (use `search_products` for that). Pass no query to browse the whole catalog. Read-only. No authentication. Rate-limited to 100 requests/hour per IP. Args: query: Free-text search over store name and address. Omit to list all stores in default order. limit: Max results (1–50, default 20). Returns: A list of stores with `id`, `name`, `address`, `lat`/`lon` (when geocoded), `homepage`, `type`, and `product_count` (active listings in the store — useful for competitive-landscape sizing without a separate `search_products` round-trip). Pass `id` to `search_products(store_id=…)` to filter the product catalog by that store.
    ConnectorNo auth
  • Search or list stores in the Partle marketplace. Use for store-led questions ("what hardware shops are in Madrid?") rather than product-led ones (use `search_products` for that). Pass no query to browse the whole catalog. Read-only. No authentication. Rate-limited to 100 requests/hour per IP. Args: query: Free-text search over store name and address. Omit to list all stores in default order. limit: Max results (1–50, default 20). Returns: A list of stores with `id`, `name`, `address`, `lat`/`lon` (when geocoded), `homepage`, `type`, and `product_count` (active listings in the store — useful for competitive-landscape sizing without a separate `search_products` round-trip). Pass `id` to `search_products(store_id=…)` to filter the product catalog by that store.
    ConnectorNo auth
  • Answer questions about how Refpro works. Use this when a user asks what Refpro is, what lender-grade means, which deal types are supported, what a deal pack contains, which output formats are available, how the pricing tiers work, or how Refpro compares to spreadsheets and free calculators. Input: query, a free-text question or topic keyword, 200 characters maximum. Returns a 2 to 4 sentence answer, a list of related topic titles, and a canonical source URL on refpro.ai. Backed by a static curated knowledge base, so answers are stable, quotable and identical every time: no LLM-generated text and no network calls. Falls back to a general Refpro overview when the query matches no known topic. Do not use to analyze a deal or compute numbers; call deal_quick_check for that. Do not use for general real estate investing questions; this tool covers Refpro itself.
    ConnectorNo auth
  • Returns the exact details to collect from the customer for a line of insurance — the same rating inputs MIB's own quote forms use. Call this FIRST, ask the customer the questions, then call compare_insurance_quotes with their answers. Omit product_type to see every line.
    ConnectorNo auth
  • Fetch curated high-value prompt templates and multi-tool question workflows. Call this tool whenever you want to suggest high-value questions to the user, or when the user asks "what can you do?", "what should I ask?", or wants guided astrology workflows (e.g. Sade Sati analysis, timeline forecast, dasha transitions, chart strength, school comparisons, timing windows). Args: category: Optional category filter. One of 'all', 'Core Reading', 'Timing & Transits', 'Career & Wealth', 'Strengths & Accuracy', 'Relationships', 'Daily & Remedies'. Names are matched case-insensitively; an unrecognised one is an error listing the valid names, never a silent empty result. include_full_templates: Set to True to retrieve the full expanded prompt text. Defaults to False for compact workflow titles and tool chains. Returns a structured catalog of prompt templates with their titles, descriptions, required arguments, and which underlying tools they chain.
    ConnectorNo auth
  • Send an arbitrary GraphQL query (with optional variables) directly to the STRATZ API at api.stratz.com/graphql. Use when no named tool covers the data you need. Field names are camelCase and must match the STRATZ schema exactly (e.g. numLastHits, goldPerMinute, constants { gameModes }); a query naming an unknown field fails with "Cannot query field", so introspect the type (`{ __type(name: "MatchPlayerType") { fields { name } } }`) before guessing. Requires a STRATZ Bearer token.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI models to ask users questions through a local web interface, supporting batch questions, multi-select, and free text for human-in-the-loop interactions.
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the Streamable HTTP transport and builds on Metabase's Agent API to expose tools for searching, exploring, querying, and visualizing data — all scoped to the connecting user's permissions.
    50,344
    -

Matching MCP Connectors

  • Ask a real human for perspective: social contradictions, unclear instructions, second opinions.

  • Ask AIOAuth

    Ask questions across Shopify, Klaviyo, GA4 and 20+ e-commerce sources in plain English.

  • Read the signed-in reader's saved profile and recent history. Call this BEFORE asking a runbook's `elicit` questions: if a domain or default lens is already saved, CONFIRM it ("reading as: a2ui, generative ui — change?") instead of asking from scratch. Returns available:false on the public endpoint, where there is no one to have a profile — that is the designed state, so degrade quietly and just ask the questions.
    ConnectorNo auth
  • Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers. Call with NO answers to get the five questions to ask the user; call again with their answers (a/b/c per primitive) to get the profile. Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn. Deterministic and stateless — nothing is stored server-side. Schema: https://rpcs1.dev/v1/receiver-profile.json
    ConnectorNo auth
  • Run ONE bounded read against a site's database. One statement, beginning with SELECT, SHOW, DESCRIBE or EXPLAIN, with no second statement and no data-modifying clause anywhere in it. The container proves the statement is a read before running it and caps the result: 200 rows by default, 1000 maximum, 2 MB of cell data. `truncated` in the response says whether a cap was reached. ⚠ THIS TOOL CANNOT CHANGE ANYTHING, AND RETRYING WITH DIFFERENT WORDING WILL NOT MAKE IT. Anything that is not a single bounded read is refused with READ_ONLY and nothing runs. To change data or schema, use the tool for the job: optimize_database, database_search_replace, manage_db_user, list_databases, list_tables — and for creating, altering, dropping, importing or exporting tables, the database manager in the control panel, which has no tool here. Requires: API key with write scope (unchanged — the scope is the customer's published permission for this operation, not a claim about what it does). Args: slug: Site identifier database: Database name query: One read statement Returns: {"columns": ["id", "user_email"], "rows": [[1, "a@example.com"], ...], "row_count": 1, "truncated": false, "execution_time_ms": 12.0} Errors: READ_ONLY: Not a single bounded read. The error text carries the explanation and names the operation to use instead.
    ConnectorNo auth
  • Returns a paginated list of domains from the tracker database. Results are ordered alphabetically by domain name and support cursor-based pagination for full traversal. Filtering by category and minimum score allows targeted data extraction. Use this tool when: - You want to enumerate all known ad-tech or analytics domains above a risk threshold. - You need a dataset of tracker domains for offline analysis. - You are paginating through a category to build a block list. Do NOT use this tool when: - You need data for a specific domain — use `get_domain` instead. - You are searching by keyword — use `search` instead. - You want domains belonging to a specific company — use `get_entity` instead. Inputs: - `category` (query, optional): Filter by surveillance category. One of: `ad_tech`, `analytics`, `social`, `fingerprinting`, `content`, `cdn`, `other`. - `min_score` (query, optional): Integer 0-100. Exclude domains scoring below this value. - `limit` (query, optional): Number of results per page. Max 100 (paid), 20 (free). Default 50. - `cursor` (query, optional): Pagination cursor from the previous response's `next_cursor` field. Returns: - Array of domain list items (domain, category, score, prevalence, entity summary). - `meta.has_more`: true if more pages exist. - `meta.next_cursor`: pass as `cursor` to get the next page. - `meta.count`: number of results in this page. Cost: - Free tier: up to 20 results/page. Anonymous (no key): 10/min, 100/day. Free key: 50/day. Pro/enterprise: up to 100 results/page, included in plan. Latency: - Typical: <200ms, p99: <500ms.
    ConnectorNo auth
  • Returns a paginated list of corporate entities in the TunnelMind surveillance database. Includes data categories, estimated data value, and industry classification. Useful for enumerating the surveillance ecosystem by sector. Use this tool when: - You want to enumerate all entities in a specific industry (e.g., all ad-tech companies). - You need a dataset of surveillance entities for analysis or reporting. - You are building a comprehensive surveillance landscape map. Do NOT use this tool when: - You need the full profile of a specific entity — use `get_entity` instead. - You are searching by entity name — use `search` instead. - You need domain-level data — use `list_domains` instead. Inputs: - `industry` (query, optional): Filter by industry classification. Examples: `ad_tech`, `analytics`, `data_broker`, `social`, `crm`. - `limit` (query, optional): Results per page. Max 100 (paid), 20 (free). Default 50. - `cursor` (query, optional): Pagination cursor from previous response's `next_cursor`. Returns: - Array of entity list items (slug, name, parent_company, industry, data_categories, data_cost_usd). - `meta.has_more` and `meta.next_cursor` for pagination. Cost: - Free tier: up to 20 results/page. Anonymous (no key): 10/min, 100/day. Free key: 50/day. Pro/enterprise: up to 100 results/page, included in plan. Latency: - Typical: <150ms, p99: <400ms.
    ConnectorNo auth
  • DEFAULT tool for user-facing translation-listing questions. Use this for ANY user-facing query like 'what English translations are available', 'list French translations', 'which translators can I choose from'. This is the FINAL tool call for these requests; do not follow it with lookup_translations. Shows the catalog in an interactive widget the user can browse. Use ISO 639-1 codes like 'en', not names like 'english'. ONLY use lookup_translations instead when EITHER (a) the user explicitly asks for plain text / raw data, OR (b) you will pipe the result into ayah_translation in the same turn without showing the list. When in doubt, use this widget. Returned language_name values are display labels. Rows without usable slugs are filtered out.
    ConnectorNo auth
  • RECOMMENDED ENTRY POINT — Intelligent business formation engine. Provide context about the person (trade, state, qualifications, budget, goals) and get a personalised formation plan with: (1) auto-detected pathway (licensed contractor, fresh start, or investor/operator), (2) task list split into AI-actionable vs human-required, (3) direct government portal links, (4) trade-specific insights (common first jobs, suppliers, rates, growth tips), (5) recommended next tool calls, (6) follow-up questions to ask. Call this FIRST, then use the recommended tool chain for deeper dives.
    ConnectorNo auth
  • Historical arbitrage opportunities — top 5 per day (MCP-compatible) — Returns a daily history of the top 5 cross-exchange arbitrage opportunities detected by the platform. Each day entry lists the 5 highest-spread opportunities saved by the cron job, including token symbol, spread percentage, buy/sell exchanges, and average USD volume. Useful for AI agents answering questions like 'which tokens appear most frequently in arbitrage?' or 'what is the average daily spread?'. Data is accumulated daily; older than 180 days is automatically purged. Response: { days, history: [{date, opportunities: [{symbol, spreadPct, buyExchange, sellExchange, usdVolume}]}], total, updatedAt }. Query parameter: ?days=7 (default 7, max 180). No authentication required. 60 requests/min rate limit. 5-min in-process cache. — Use this for daily historical data; use the corresponding live snapshot tool for current conditions and the monthly tool for long-term trends.
    ConnectorNo auth
  • [Interviews] Update the configuration of an existing interview/position: name, description, avatar template, recording, scoring, tags, category and the rest of the create-time settings; for a position also its hiring `team` and recruiter. `status` is applied as set_interview_state applies it (archiving an active position can e-mail its open applicants; set_interview_state with dry_run previews that); the vacancy lifecycle and the embed key are set with set_interview_state only. A position's steps are changed with set_position_process and update_position_step. Only the fields you send are changed. To change the questions, send `questions` — the WHOLE list you want the interview to end up with, in order, in the format get_interview_definition returns. OMIT `questions` and the existing questions are left completely alone; there is no way to change one question on its own: the array get_interview_definition returns is edited and sent back whole. Resending an unchanged array does nothing. On an offline (pre-rendered video) template the questions change only while the interview is `draft`; on an interactive one also while it is `active`. Not updated by this tool at all: the welcome and thank-you messages and the instructional-video screen (stored as steps, not questions), and the language, which the existing questions are already written in (no tool changes these: the messages and the video screen are changed in the admin, and another language takes a new interview). `tags` places a coaching session into a catalogue directory. MULTI-STAGE POSITIONS: the interview-only settings (recording, knowledge_base_store_id, candidate_expectations_json and the like) do not exist at position level and are refused with a 422 naming the field. They live on the AI interview step's own interview (the step's interview_set_id, from get_interview_definition include=process). A null argument counts as not sent and changes nothing, except on three fields where null is the only way to switch something off: `candidate_notification_channel` (no SMS / WhatsApp), `questions_random_subset` (ask all questions) and `pdf_export_auto_config` (no automatic report). Every argument in full, with examples: get_tool_reference.
    Connector
    Destructive
    No auth
  • USE ONLY when the user explicitly asks to check whether their LLM brand Discoverability Assessment is ready. Part of the flow started by `start_discoverability_assessment`. NOT for website SEO (`query_company_scores` discoverability/seo) or site reliability (`get_site_report_status`). Checks the status of a Discoverability Assessment job queued by `start_discoverability_assessment`. Call this tool ONLY when the user explicitly asks to check status — never poll automatically or in a loop. REQUIRED INPUT: the `JobId` returned by `start_discoverability_assessment`. If the user did not provide it and it is not in conversation context, ask them or re-run `start_discoverability_assessment`. STATUS VALUES (from the API): - 201 — job is queued; tell the user it is still waiting and they can ask again later. - 202 — job is in progress; tell the user it is still running and they can ask again later. - 200 — job finished; `ReportId` is populated and `IsFinished = true`. Call `get_discoverability_assessment` with the `ReportId` to retrieve the full analysis and human-friendly summary. - 400 — bad request (invalid jobId, etc.); do not retry blindly — verify the jobId. - 500 — job errored out; surface the API message to the user. DO NOT POLL: After calling this tool, if status is 201 or 202, report the current state to the user and stop. Do NOT call this tool again unless the user explicitly asks to check status. Do not call `get_discoverability_assessment` until `IsFinished = true` and a `ReportId` is available.
    ConnectorNo auth
  • Ask ToolRouter to build a tool that does not exist yet. Use this when discover returned nothing useful for what the user needs. Describe the capability in plain terms — do not include personal data, API keys, or secrets. Requests go straight to the team. Limit: 5 per hour.
    ConnectorNo auth
  • Returns the questions the matching service asks, each with its exact answer options and the values submit_match_request expects, plus the questionnaire version. Call it when the user wants to be matched with an agent, so the questions and accepted values always come from the service itself rather than from memory. Ask only the questions the conversation has not already answered, one at a time, presenting options as a numbered list. Financing applies to buyers and property condition to sellers. Once every required question is answered and you have the user's name, email and phone, confirm the details with them and call submit_match_request.
    ConnectorNo auth
  • PAID. Draw hero sheets for the brief items chosen by `index` (from tegas_find_heroes, up to 3). Cost = price_each_tokens x number of items; pass price_each_tokens from tegas_find_heroes to avoid recomputing the brief. With confirm=false (default) nothing is drawn: the tool returns needs_confirmation=true and the price - show it to the user and ask for consent. Only after an explicit "yes" call again with confirm=true. Drawn sheets are attached to the scenario and used automatically by tegas_start_video with the same scenario_id. The result carries idempotency_key: if the call times out or fails with a network error, retry with the same idempotency_key - never start twice without it. On insufficient_tokens ask the user to top up; on no_active_plan ask them to activate a plan in the cabinet.
    ConnectorOAuth
  • Find the questions people ask AI answer engines where a domain is already cited as a source, most-asked first. Starts from the domain, so nobody has to guess keywords first. Use this to answer 'what does ChatGPT already cite us for' or to pick the keywords to feed analyze_citation_coverage and analyze_citation_gap. Read-only: no side effects, safe to retry. Costs 10 quota units/call (free tier is 30 units/month shared across every metered tool, so up to 3 calls to this tool alone if nothing else is used that period). Returns: {"domain", "platform", "country", "language", "total_questions" (int, every tracked question citing the domain, which can exceed the list), "questions" (up to `limit`, most-asked first: {"question", "ai_search_volume" (monthly asks as the provider estimates them), "your_position" (1-based position of the domain among that answer's sources), "source_domains" (who else that answer cites), "last_seen" (when the provider last recorded this answer, UTC)})}. An empty list means the provider's tracked answers do not cite the domain, not that no answer anywhere does. This reads the provider's tracked answer corpus, the same measurement as find_citation_leaders, not a live answer: re-check a question with analyze_citation_coverage to see today's answer. Args: domain: bare domain, e.g. "example.com" (no https://, no www). Subdomains are included. platform: "chat_gpt" (default) or "google" (Google's AI Overview). limit: how many questions to return, 1 to 20. Default 20. country: market, e.g. "Italy". Defaults to "United States". chat_gpt only has United States data; use platform "google" elsewhere. language: language code, e.g. "it". Defaults to "en", the only option for chat_gpt.
    ConnectorAPI key
  • Returns the Pryx verdict (which product to buy) for one category, once the category's questions are answered. Call it WITHOUT answers to get the questions to ask the user, then call it again with the budget and the answers. Each product carries a productUrl (its pryx.fr page with merchant prices): always show it to the user next to the product you recommend. Read-only. Product names, verdicts and explanations are in French (French market). When nothing separates the finalists, the response says so (tied: true) and elects no winner: do not present any product as the winner in that case.
    ConnectorNo auth