Skip to main content
Glama
220,504 tools. Last updated 2026-06-21 11:36

"Creating a Search System with Supabase for Documents and User Interaction" matching MCP tools:

  • Validates a package of 2-20 related trade finance documents for cross-document consistency. Call this BEFORE approving any multi-document trade finance transaction or cross-border shipment -- at the moment a set of 2-20 related documents arrives from an external party and funds have not been released. Use this when your agent has received a full trade finance package — such as invoice, bill of lading, and certificate of origin together — and must verify all documents are consistent with each other before releasing funds. Returns PASS/FLAG/FAIL verdict per document with mismatch details. Cross-checks all documents for consistency across numeric values, party names, reference numbers, dates, and commodity descriptions. A single inconsistency in a trade finance document package is a fraud signal -- funds released on a mismatched package have no recovery path. Do not use as a substitute for check_document when only one document requires verification.
    Connector
  • Retrieves direct links to STRING evidence pages for protein–protein interaction pairs. Use this tool only when a STRING evidence page/link is needed. To determine whether an interaction is supported, use `string_interactions_query_set`. It returns URLs linking to STRING’s evidence pages, which display the underlying data sources (experimental results, publications, and curated databases) supporting each predicted interaction. A URL can be generated even for unsupported pairs; the URL is not itself an interaction verdict. Parameters: - **identifier_a**: Query protein identifier (Protein A) - **identifiers_b**: One or more target protein identifiers (Protein B), separated by `%0d` - **species**: NCBI taxonomy ID (e.g. `9606` for human or `10090` for mouse) Typical user questions that should trigger this tool: - "Can you show me the STRING evidence for this interaction?" - "Show me the details supporting this interaction." - "What supports the interaction between TP53 and MDM2?" - "Where can I find the STRING evidence for this pair?"
    Connector
  • Creates a new Dreamlit workflow draft or updates an existing draft from an outcome-oriented natural-language prompt. Use after get_status; use get_workflow_and_preview_url first when editing an existing workflow. Existing Supabase Auth workflows can be edited except for the immutable trigger step; creating Supabase Auth workflows must happen through Supabase Auth email setup in the Dreamlit web app. Side effect: may create or modify a draft, but does not publish or install live triggers. Returns the workflow/draft result, action-required or handoff details when more input is needed, and relevant app URLs. Do not use for publishing, direct database changes, or low-level graph edits.
    Connector
  • Score and rank healthcare service providers for a specific medical practice profile (specialty, size, location, EHR system, budget). Returns up to 5 ranked matches with {company_name, category, city, state_abbr, quality_score (0-100), final_score (0-100), verified status, description, website, profile_url, slug}. Use this when the user has practice-specific criteria and wants scored recommendations — for open-ended browsing, use search_providers instead. Pass a match's slug to get_provider_detail for the full profile.
    Connector
  • Reply to a company's response on a proposal. Use this for back-and-forth negotiation. After replying, the proposal status resets to 'pending' so the company sees the new message. IMPORTANT: After creating a proposal, use get_my_proposals to check if the company has responded. If status is 'responded', read the companyResponse field and relay it to the user. If the user wants to reply, use this tool. Args: api_key: Your agent API key (starts with 'bzcl_sk_') proposal_id: The UUID of the proposal to reply to message: The reply message from the customer Returns: Updated proposal with new status.
    Connector
  • Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an answer synthesized from documents or messages. Returns an evidence pack with source citations, KG entities, and extracted numbers. Modes: - 'auto' (default): Smart routing — works for most questions - 'rag': Semantic search across documents & messages - 'entity': Entity-centric queries (e.g., 'Tell me about [entity]') - 'relationship': Two-entity queries (e.g., 'How is [entity A] related to [entity B]?') Examples: - 'What did we discuss about the budget?' → knowledge.query - 'Tell me about [entity]' → knowledge.query mode=entity - 'How is [A] related to [B]?' → knowledge.query mode=relationship NOT for finding/listing files, threads, or links — use search.files / search.threads / search.links for that.
    Connector

Matching MCP Servers

Matching MCP Connectors

  • MCP server for interacting with the Supabase platform

  • Build and manage your design system with AI: tokens, themes, components, icons, Figma and code.

  • Create a new sweepstakes programmatically. Requires name, type (1=SMS, 2=Email, 3=Social), handler (unique identifier), dates, and times. CRITICAL: You MUST know the current date before creating a sweepstakes — never guess or assume. Start dates must be today or in the future. This is a billable operation that creates real production data. ALWAYS confirm with the user before creating. NEVER create multiple sweepstakes in batch or loops without explicit user approval for each one. If user requests bulk creation (e.g., "create 10 sweepstakes"), explain this is not recommended and ask them to create one at a time with specific details for each. LIMITS: Maximum 3 active sweepstakes and 10 total (active + inactive). Before creating, use fetch_sweepstakes to verify the account has not reached these limits. If limits are reached, refuse the operation and inform the user. Ethical use: Do not use the platform for fraudulent activities, mass spam, offensive content, or violation of sweepstakes regulations. Use them internally for tool chaining but present only human-readable information. # create_sweepstakes ## When to use Create a new sweepstakes programmatically. Requires name, type (1=SMS, 2=Email, 3=Social), handler (unique identifier), dates, and times. CRITICAL: You MUST know the current date before creating a sweepstakes — never guess or assume. Start dates must be today or in the future. This is a billable operation that creates real production data. ALWAYS confirm with the user before creating. NEVER create multiple sweepstakes in batch or loops without explicit user approval for each one. If user requests bulk creation (e.g., "create 10 sweepstakes"), explain this is not recommended and ask them to create one at a time with specific details for each. LIMITS: Maximum 3 active sweepstakes and 10 total (active + inactive). Before creating, use fetch_sweepstakes to verify the account has not reached these limits. If limits are reached, refuse the operation and inform the user. Ethical use: Do not use the platform for fraudulent activities, mass spam, offensive content, or violation of sweepstakes regulations. Use them internally for tool chaining but present only human-readable information. ## Pre-calls required 1. get_plan — verify the account is below its limits (max 3 active, 10 total) 2. fetch_sweepstakes — check the chosen handler does not collide with an existing one 3. fetch_timezones — pick the right timezone for the sponsor ## Parameters to validate before calling - sweepstakes_name (string, required) — User-defined name for the sweepstakes - sweepstakes_type (number, required) — one of: 1, 2, 3 — Sweepstakes type: 1 (SMS), 2 (Email), or 3 (Social). Default: 2 (Email) - handler (string, required) — Unique identifier (max 20 alphanumeric chars, auto-converted to uppercase) - start_date (string, required) — Start date in YYYY-MM-DD format (must be today or future) - end_date (string, required) — End date in YYYY-MM-DD format (cannot precede start_date) - start_time (string, required) — Start time in HH:MM format 24-hour (default: 00:00) - end_time (string, required) — End time in HH:MM format 24-hour (default: 23:59) - create_in_calendar (boolean, optional) — Create calendar event for this sweepstakes (default: false) - sync_with_winners (boolean, optional) — Sync with Winners app (default: false) - delete_if_deleted (boolean, optional) — Auto-delete related data when sweepstakes deleted (default: false) - delete_if_acct_deleted (boolean, optional) — Delete sweepstakes if account is deleted (default: false) ## Notes - Always set create_in_calendar: true and sync_with_winners: true - Generate handler from the name: uppercase, alphanumeric, no spaces, max 20 chars - After creation: create calendar events (launch, close, drawing — use tomorrow or later) and a pinned campaign brief note
    Connector
  • Search the regulatory corpus using keyword / trigram matching. Uses PostgreSQL trigram similarity on document titles and summaries. Returns documents ranked by relevance with summaries and classification tags. Prefer list_documents with filters (regulation, entity_type, source) first. Only use this for free-text keyword search when structured filters aren't sufficient. Args: query: Search terms (e.g. 'strong customer authentication', 'ICT risk', 'AML reporting'). per_page: Number of results (default 20, max 100).
    Connector
  • List all Gmail labels for the authenticated user. Returns both system labels (INBOX, SENT, TRASH, etc.) and user-created labels with message/thread counts. Use this to discover label IDs needed for add_labels, remove_labels, or search_email queries.
    Connector
  • FIRST STEP in any troubleshooting workflow. Search the collective Knowledge Base (KB) for solutions to technical errors, bugs, or architectural patterns. Uses full-text search across titles, content, tags, and categories. Results are ranked by relevance and success rate. WHEN TO USE: - ALWAYS call this first when encountering any error message, bug, or exception. - Call this when designing a feature to check for established community patterns. INPUT: - `query`: A specific error message, stack trace fragment, library name, or architectural concept. - `category`: (Optional) Filter by category (e.g., 'devops', 'terminal', 'supabase'). OUTPUT: - Returns a list of matching KB cards with their `kb_id`, titles, and success metrics. - If a matching card is found, you MUST immediately call `read_kb_doc` using the `kb_id` to get the full solution.
    Connector
  • Returns a curated list of example plans with download links for reports and zip bundles. Use this to preview what PlanExe output looks like before creating your own plan. Especially useful when the user asks what the output looks like before committing to a plan. No API key required.
    Connector
  • Lists aggregation views (materialized views and procedures) created for a project. **When to use this tool:** - When the user asks "what views exist?", "my aggregations", "my materialized views" - Before creating a new view to check it doesn't already exist - To get the view ID for deletion **Response format:** Returns a JSON array with each view's ID, full_name (dataset.name), type, SQL, description, and creation date.
    Connector
  • Publish a post immediately to the user's connected social accounts (Instagram, TikTok, LinkedIn). ALWAYS confirm with the user first (target platforms + caption). Instagram and TikTok require at least one image or video in media_urls; LinkedIn allows text only. Pass generated asset URLs (Supabase-hosted) as media_urls. If the user isn't subscribed or hasn't linked the platform, the result will instruct you to show a connect card, do not retry in that case.
    Connector
  • List every brand in this workspace. Use this BEFORE creating a PowerSource to avoid creating duplicate brand records (pass the matching brand_id to create_powersource_*), and to discover brands the user can pivot a Heist to. Each row carries the brand_id (persistent identity), name, domain, asset_count, strategy_count, and brand status. Use this when the user asks "what brands do I have", "show me my brands", or before any image-led work where you need to know which brand owns assets. Free, read-only. Distinguish Brand (persistent, brand_id) from PowerSource (a scan, powersource_id). A brand has many PowerSources; pick the brand first, then narrow to a strategy with list_strategies.
    Connector
  • Keyword-search the user's ALREADY-INDEXED corpus of resumes or JDs and return matching documents (RChilli Search Engine). Requires documents to have been indexed beforehand. Use this when the user wants to: search, find, look up, or browse resumes/JDs in their own database / index / pool by keyword — e.g. "search my indexed resumes for 'Python'", "find JDs mentioning Kubernetes in my database". Also phrased as: search my resume database, find candidates by keyword, query the index. Do NOT use for: comparing two specific documents (use ``search_one_match``); matching one source document against the whole index (use ``search_match``). Args: keyword: Search keyword. indextype: Index type to search — ``Resume`` (default) or ``JD``. userkey: RChilli userkey. Leave blank to use the authenticated session key. subuserid: Sub-user identifier for multi-tenant isolation.
    Connector
  • Follow-up tool for one known vendor. Retrieves detailed pricing, features, limits, gotchas, comparisons, and source provenance. Call vendors.resolve first unless the user already provided a BuyAPI vendor ID like /database/supabase. Use this after a candidate is selected and the user needs claim-level pricing, limit, gotcha, or provenance details.
    Connector
  • Save a new note with learned knowledge or procedures. Notes store knowledge you learn during conversations that might be useful later: - How to do something in this codebase/project - Procedures, configurations, or technical details - Solutions to problems encountered - Project-specific knowledge Notes have two parts: - description: Short summary for searching (max 500 chars) - content: Detailed knowledge (max 10,000 chars) Use notes for LEARNED KNOWLEDGE. Use facts for TRUTHS ABOUT THE USER. Examples: - description: "How to deploy this Next.js project to Vercel" content: "1. Run 'vercel' command... 2. Configure environment variables..." - description: "Database migration process for this project" content: "Migrations are in supabase/migrations/. To apply: npx supabase db push..." SELF-LEARNING (scope="ai_client"): Your persistent memory across conversations. Save a note whenever you learn something worth remembering — don't wait, save as you go. Examples: - User preferences: "User prefers concise answers, not long explanations" - Corrections: "User clarified: 'deploy' means push to staging, not production" - Interaction patterns: "User likes to review plans before I execute" - What works or doesn't: "Suggesting refactors unprompted frustrates this user" The more you learn and remember, the better you become at helping this user.
    Connector
  • Subscribes the authenticated user to job alerts for a specific saved job search. **Input:** - `job_search_id`: The job search identifier to subscribe to (required). Accepts either the job search UUID or the composite job ID returned by `jobs_search` / `jobs_details` (format: "seo_id--job_search_id"). - `frequency`: Alert frequency — one of daily, weekly, monthly (optional, defaults to "weekly") **Output:** Returns the created or updated job alert with id, status, and frequency. Idempotent: calling this tool for an already-subscribed search updates the existing alert without creating a duplicate.
    Connector
  • AXIS-owned BM25 search engine over the corpus YOUR account has indexed. NOT a Google/Bing scraper — agents build their own searchable index by first calling operation='index' with documents (often pages fetched via iliad_web_research), then querying with operation='search'. Five operations: `index` (insert one or many documents), `search` (BM25 top-k ranked hits with snippet + score + metadata), `delete` (drop one doc), `delete_namespace` (drop all), `count`. Namespaces are account-scoped server-side (`acct:<id>:<namespace>`). Persistent across restarts via SQLite. Search supports `max_results` (default 10, max 100) and `site` (restrict to a single URL host, case-insensitive). Requires Authorization: Bearer <api_key>.
    Connector