"Converting Natural Language to SQL Queries" matching MCP tools:

• vibekit_db_query

  VibeKit

  Run a read-only SQL query against an app's Postgres database and return up to 200 result rows. SELECT only — writes and DDL (INSERT/UPDATE/DELETE/ALTER/DROP/…) are rejected server-side; use vibekit_chat or vibekit_submit_task to have the agent make data or schema changes. Call vibekit_db_schema first to learn the tables. SQL string, max 5000 chars.

  Connector

• fx_list_currencies

  exchange-rates-mcp-server

  List all supported ISO 4217 currency codes with their full names. Call this before converting to disambiguate "dollars" (USD vs AUD vs CAD vs HKD vs SGD) or to validate a user-supplied currency code. Covers the ~30 ECB reference currencies.

  Connector

• list_events

  ClearMarket

  Browse or search ClearMarket prediction-market events. Filter by category, platform, Resolution Clarity Grade, or free-text `q`. `q` is token-AND across question + tags, so SHORT KEYWORD queries match best ("microstrategy bitcoin", "fed rate") — natural-language phrases often return nothing. Returns compact graded summaries: slug, question, venues_covered, primary grade, rcg_score (0-100, for ranking clarity), last_price, and status (open / resolved). Start here when you have a topic but not a slug; then call get_event for the full graded record. Categories: economics, financials, crypto, companies, technology, politics, geopolitics, health, climate.

  Connector

• search_listings

  SPACEXPLORATION

  Search commercial real estate listings. Returns paginated hits with facet counts. For AI-driven search, call interpret_search first to convert a natural-language query into structured filters, then pass those filters — and its bounds, when present — here.

  Connector

• interpret_search

  SPACEXPLORATION

  Translate a natural-language property-search sentence into a structured filter payload compatible with search_listings. Use this as a transparent intermediate step: pass the user's raw query here, then forward the returned filters — and the returned bounds, when present (they carry the "near <place>" intent) — to search_listings.

  Connector

• mu_spec_draft

  mu

  Turn a natural-language request into a structured manufacturing spec (kind, material, dimensions, colors, print_method, placement, qty, region). Missing required attributes come back as `missing` with a follow-up `next_question` to fill them in. Feed the resulting spec_id into mu_rfq_create. Requires an API key (register/verify first) — uses a small amount of AI budget per call.

  Connector

• quote

  FlowVolt

  Direct quote path. Use when the user already knows who they want to reach and just asks for pricing or to find leads. Takes a natural-language description and returns six plans in plain prose. For users who haven't expressed their ICP yet, prefer discover_business which tailors the response. Pass `name` and `company` if you know them.

  Connector

• search_workspaces

  FrankSpace Public MCP

  Search live UK workspace listings on FrankSpace. Filter by location text (city, postcode, submarket), size band, and maximum monthly price (pence). For richer natural-language queries prefer `ai_search`.

  Connector

• search_bookmarks

  linkedmash

  Search through a user's LinkedIn bookmarks using either keyword (text) search or semantic (meaning-based) search. Supports all list_bookmarks filters, full-text search via the q field, and semantic search via the vector_search_term field for natural language or topic-based queries. IMPORTANT: At least one of 'q', 'vector_search_term', or 'author' must be provided. If the user asks to find posts by a specific author (e.g., 'Show posts by John Doe', 'Find posts from Suresh sambantham'), use the 'author' parameter instead of putting the author name in the 'q' field. Use 'q' for searching post content, not for filtering by author.

  Connector

• scalix_db_text_to_sql

  Scalix Cloud

  Translate a plain-language question into a candidate SQL query using pattern-matching against the live schema (no AI model — simple questions only: counts, averages, filtered selects on a named table). Returns the SQL without executing it, with a confidence score; low confidence means the table was guessed. Review the statement and tables_used, then run it with scalix_db_query. For complex questions, read scalix_db_schema and write the SQL directly.

  Connector

• polybridge_search

  PolyBridge

  Search public prediction markets for markets relevant to a natural-language topic or question. Use when you need candidate markets, market URLs, outcomes, statuses, and relevance scores. Do not use for a final probability forecast, market-history lookup, trading, or private/internal data. Scores are relevance scores, not probabilities.

  Connector

• route_market

  Mantis

  Find the best prediction market for a natural-language question or trading intent. Returns the best cross-venue match, current probability, liquidity, and any arbitrage opportunity between venues.

  Connector

• search

  Pollar News

  Searches Pollar's published news and returns a ranked list of matching articles as {id, title, url}. Use for queries about a subject, person, organisation, place, or country; put that subject or place in query. Locale controls response language, not geographic scope. Pass an id to fetch to read the article.

  Connector

• director_note

  framesail

  Edit ONE scene with a natural-language note (the same director chat the editor UI uses): move/restyle/add/remove layers and overlays, retime, etc. Synchronous — returns the applied mutations + updated scene. Use list_scenes to find scene ids; for notes spanning the whole video use project_director_note instead.

  Connector

• query_data

  Algenta MCP Server

  Execute a structured query against connected data sources. Convert the user's question to a structured intent and call this tool — do NOT try to write SQL or parse column names yourself. The engine resolves column meaning from mathematical relationships and statistical structure only. It works on any dataset without configuration. The governed filter shape is a record-predicate contract over normalized rows, not a SQL predicate language, so it also applies to Redis and other non-SQL sources. Structural roles (use in metric.role): - derived_measure: the main financial/operational aggregate (revenue, spend, value) - base_measure: counts, quantities, discrete amounts - unit_measure: per-unit prices, rates - ratio: percentages, margins, fill rates (0-1 range) - metric: let the engine pick the best numeric column If clarification_required is true, or if confidence < 0.85, check the candidates list and ask the user to clarify. Never fabricate column names or SQL.

  Connector

• ask_directory

  Laspi Business Directory

  Ask the directory a customer question in natural language. Returns schema.org cards of businesses that genuinely answer it (LLM-reranked, strictly from the directory — never invented) + grounding links. Use when the customer describes a NEED rather than a search term.

  Connector

• semantic_search

  Agentic.ai Directory

  Search for AI tools using natural language with AI-powered semantic matching. Best for conceptual queries like 'something that automates my email workflow'. Supports structured filters to narrow results (e.g., openSource + deploymentModel). For exact name/keyword searches, use search_listings instead. For comparing specific tools, use compare_listings.

  Connector

• search_products

  agenticfeed

  Find a merchant's products that match a shopper's need, question, problem, or use case. Pass the buyer intent in natural language (e.g. "a light strategy game for 4 players under thirty pounds"); returns ranked in-stock products with the reason each fits, drawn from Agenticfeed's intent mapping (questions, problems, use cases). Call find_merchant first to get the merchant ID.

  Connector

• recommend_mcp_for_task

  mcpindex

  Recommend the best MCP servers for a natural-language task. Returns top 3 ranked picks with reasoning, install commands, and quality scores. Use this when the user asks for the right MCP server for a task they want to do.

  Connector

• askQuestion

  BlockRazor Docs

  Ask a natural-language question about BlockRazor and get a synthesized answer, with links to the source pages. Prefer this over `searchDocumentation` when you want a direct answer to a question rather than a list of matching pages; use `searchDocumentation`/`getPage` when you need to browse or read full pages yourself.

  Connector