"SQL-Based Technologies or Concepts" matching MCP tools:

• vibekit_db_queryA

  VibeKitA

  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.

  ConnectorNo auth

• query_nem_dataA

  nempulseA

  Last resort for ad hoc questions the other tools cannot answer. Takes a plain-English question, generates SQL over NEMPulse's tables, and returns the SQL, the result rows and a short explanation. It is the slowest tool (can take close to a minute) and it is AI-generated, so check the returned SQL before relying on a number. Scope each question to about one region-month or less: wider aggregates (a full year by region, or per-day top-N across all regions) risk exceeding the 8 second SQL limit, and a longer wait does not help. For per-day top-N or bottom-N questions, ask for a window function (ROW_NUMBER or RANK) rather than a per-day subquery, which has been seen to silently return all-null rows. Queryable data: dispatch prices, daily revenue, optimal dispatch, battery price profiles and market events. The market analysis tables (monthly spreads, regressions, correlations) are not reachable here.

  ConnectorNo auth

• cross_checkA

  Plumbline — a trust layer for LLM answersA

  Corroborate a figure you obtained (e.g. from run_sql) against the verified fact store: it re-derives the named value_key from the same SQL the verified pipeline uses and compares. AGREE lifts an otherwise-unverified session to 'corroborated'; DISAGREE marks a CONFLICT (worse than unverified). This is the only way a raw figure earns trust back, and it can only ever agree with a number the fact store itself computed. Resolvable keys cover the single-snapshot fact concepts plus temporal and per-department growth keys (e.g. indexed_people.<dept>); per-question keys (a named department's median, one person's direct-report count) return unmapped.

  ConnectorNo auth

• get_query_patternsA

  Shibui FinanceA

  REQUIRED before stock_data_query, 23 SQL patterns prevent timeouts/wrong results Must be called once per session immediately after get_database_schema. Contains query patterns for time-series selection, return calculations, screening joins, window functions, backtesting, and performance optimization. Time-series queries will timeout or return wrong results without these patterns. After this tool returns, call stock_data_query to execute SQL.

  ConnectorNo auth

• get_query_patternsA

  Shibui FinanceA

  REQUIRED before stock_data_query, 23 SQL patterns prevent timeouts/wrong results Must be called once per session immediately after get_database_schema. Contains query patterns for time-series selection, return calculations, screening joins, window functions, backtesting, and performance optimization. Time-series queries will timeout or return wrong results without these patterns. After this tool returns, call stock_data_query to execute SQL.

  ConnectorNo auth

• get_skill_clustersA

  nü people Job ServerA

  Returns the current skill cluster data for public jobs on the nü people website. Use this tool when the user wants an overview of which skills or technologies are currently in demand.

  ConnectorNo auth

• prepare_contextA

  remnusA

  Build a task-specific, token-budgeted context pack from the most relevant pages: lexical rank, human-reviewed knowledge preferred, stale/deprecated concepts penalized, plus the top hits' link neighbors. Use it before multi-page product or coding work instead of many search/get_page calls.

  ConnectorOAuth

• get_company_overviewA

  UpforgeA

  Who Upforge is: what they build, who founded and runs it, where they're based, how long they've been operating, how to reach them, and the technologies they work in. Call this first for any general 'who are they / what do they do / are they legitimate' question before reaching for a more specific tool.

  ConnectorNo auth

• query_datasetA

  Misata Studio: verified synthetic dataA

  Read-only SQL over a dataset's own tables (one SELECT/WITH statement; every table name is a view over that dataset's own files — nothing else on the server is reachable this way). Args: dataset_id: from a prior generate_dataset call. sql: a single SELECT (or WITH ... SELECT) statement. No semicolons, file paths, or statements that write or read outside the dataset (checked before running). limit: rows returned (capped at 5000). Returns: columns, rows, truncated (whether more rows existed than `limit`).

  ConnectorNo auth

• plan_image_conceptsA

  MondovoB

  Price a set of private image concepts without making anything: 1 Creative Credit per concept, refunded for any that fail. Send the returned `credits` as `expected_credit_cost` on explore_image_concepts.

  ConnectorOAuth

• explore_image_conceptsA

  MondovoB

  Generate 1–3 private image concepts for a hero, a section or an image replacement, so the user can compare directions before anything on the site changes. SPENDS Creative Credits: call plan_image_concepts first and send its `credits` as `expected_credit_cost` with a stable `idempotency_key`; a different price is refused with nothing charged. Failed concepts are refunded. The site is NOT changed — to use a concept, call apply_image_replacements with its concept_library_id (free).

  ConnectorOAuth

• validate_sqlA

  sqlai.dev SQL VerifierA

  Validate a SQL query against a schema WITHOUT executing it (parse + name/type binding via EXPLAIN). Returns ok with referenced tables, or a structured error: {type: unknown_column|unknown_table|syntax|..., message, position, suggestion}. The suggestion is rule-based (edit distance against your schema). Example: query "SELECT nmae FROM users" → error type unknown_column, suggestion 'did you mean "name"?'.

  ConnectorNo auth

• saved_queriesA

  ThinAir DataA

  Personal, named library of reusable SELECT queries — save once, run by name later, instead of re-pasting SQL or scanning query_history's backward-looking log. action=save stores sql under name (fails with name_exists if taken — delete first to replace). action=run executes the stored SQL through the same read-only guard and firewall as query_sql and returns up to 100 rows. action=list returns saved queries (up to 100), optionally filtered by tag. action=delete removes one by name or id. save/run/delete write to tenant storage; list is read-only. All four actions count against daily quota. Returns the saved record, a result table (run), the query list, or a delete confirmation. [BUILD tier]

  Connector

  Destructive

  OAuth

• query_firewallA

  ThinAir DataA

  Manage and test per-connection SQL firewall rules that block, warn, or log matching queries — distinct from pii_scan, which scans stored data (not SQL text) for PII. action=add_rule creates a rule (rule_name + RE2 pattern; optional block_action: block/warn/log, default block — only "block" is enforced, "warn"/"log" are advisory-only). action=remove_rule deletes by name or id. action=list_rules is read-only. action=test_query checks a sql string against the built-in guard plus your rules and returns a verdict without running it. add_rule/remove_rule write; changes take effect within 60s. All actions count against quota. Limits: 50 rules/connection, 512-char patterns. [ARCHITECT tier]

  Connector

  Destructive

  OAuth

• extract_entitiesA

  AI-SEO / AEO / GEO AuditA

  Extract named entities, linked concepts, and sameAs graph nodes from a page's content and structured data. Combines body-text NER with JSON-LD `@type` / `sameAs` walking. Read-only when given `url` (one HTTP GET). Zero network when given `text`. Primary path: MCP sampling - the host LLM does the NER and returns typed entities with sameAs URIs. Fallback path: deterministic regex-based extractor when sampling is unavailable. The result includes `mode: "sampling" | "regex_fallback"` so callers can tell which path ran. When to use: building an entity map for schema generation, or auditing whether a page's entities match its target topic. To validate the JSON-LD itself, use `audit_schema`. Either `url` or `text` must be provided.

  ConnectorNo auth

• fastero_update_queryA

  FasteroA

  Change a saved query’s name or SQL text; fields not sent stay as they are, and its connection cannot be changed here. New SQL must be read-only, as for fastero_create_query. Every report, dashboard chart and alert built on the query reads the new SQL from its next run, and a chart plotting a column the new SQL no longer returns stops drawing it. The old SQL is not kept. When the SQL changes, send definitionsUsed again so it is restamped at the current version.

  Connector

  Destructive

  API key

• get_financialsA

  Edgar — SEC Company Financials for AI AgentsA

  Standardized financial statements for one company from its SEC EDGAR XBRL filings — revenue, net income, EPS, cash flow, and balance-sheet concepts per fiscal period, latest periods first. Use for period-by-period statements; use get_metric_history instead for one concept's long time series, and list_financial_concepts to see which concepts exist. Read-only; no API key. Values are cleaned: when a period was reported more than once the latest filing wins, fiscal periods are verified, and two concepts (total_liabilities, gross_profit) may be derived from reported components and are tagged 'derived:' in their source tag. Every value carries per-value provenance (form, filed date, accession number). Identify the company by ticker or CIK (CIK wins if both are given). Coverage loads progressively — roughly 25 more companies refreshed per day, priority tiers first — so a valid company can legitimately return 'no financials stored yet'.

  ConnectorNo auth

• secedgar_search_conceptsA

  secedgar-mcp-serverA

  Search supported XBRL financial concepts by keyword, statement group, or taxonomy. Use before secedgar_get_financials, secedgar_compare_companies, or secedgar_fetch_frames to discover the right friendly name, or pass a raw XBRL tag (e.g., "NetIncomeLoss") to reverse-lookup which friendly names map to it. Empty search with no filters returns the full catalog.

  ConnectorNo auth

• get_platform_trendsA

  rankparse-mcpB

  Get a ranked list of all detectable platforms and technologies with their domain counts, useful for comparing platform adoption (e.g. how many sites run WordPress vs Shopify)

  ConnectorNo auth

• edgar_get_factsA

  SEC EDGARA

  Get XBRL-structured financial facts for a company (revenue, operating income, net income, cash, assets, etc.). Accepts common-name aliases ('revenue', 'eps') OR XBRL concepts ('Revenues', 'EarningsPerShareDiluted'). Returns one row per (fiscal_year, fiscal_period), preferring latest-filed when amendments exist.

  ConnectorNo auth

• delete_angleA

  GrowomatA

  Delete an angle. Its concepts are deleted with it; ads keep their stamp (dangling but queryable). Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.

  Connector

  Destructive

  API key