Skip to main content
Glama
619,939 tools. Updated 2026-09-28 21:07

"Database search and analysis tool" matching MCP tools:

  • 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
  • Search for restaurants near a location. For picking where to eat or giving recommendations, use recommend; this tool is for browsing a list by distance or filters. Returns graded, ranked results with cuisine, price level, and Seemor analysis summaries. Fully analyzed restaurants (coverage_level 'full', letter grade) come first; when fewer than `limit` are available, quick-read restaurants are appended after them, marked coverage_level 'basic' with grade null and a preliminary_band (e.g. 'A-range') graded from review analysis, not star ratings. total_in_area = analyzed_in_area + preliminary_in_area; a message explains when quick-read rows are included.
    ConnectorNo auth
  • Verify MCP server connectivity. Returns success immediately with no database calls. Use this FIRST if experiencing tool errors - a successful response confirms the server is reachable. It does not confirm account, search, or paid-feature authentication, which can still return "Auth required" separately. Does not count toward your monthly searches.
    ConnectorNo auth
  • Search Amazon by keyword or a full search/category URL and get structured product listings: ASIN, title, price, rating, review count, Prime status, and badges (Best Seller, Amazon's Choice) for each result. Also returns the available refinement filters (category, brand, price range) with their IDs. Use this tool for market research, keyword analysis, and product discovery. If the user already has an ASIN or product URL, do NOT search — use get_product_detail directly. Each page costs 1 credit. One page typically returns 20-40 products, which is enough for most questions. Use sort_by and exclude_sponsored to improve result quality instead of fetching more pages. To filter by category or brand, first run one search and read the refinements field in the response to discover valid filter IDs, then pass them in refinements.
    ConnectorNo auth
  • Initializes a Blockscout MCP session: returns server reference data, the `blockscout-analysis` skill pointer, and the URI resolution rule. Call this tool exactly once per session, before any other tool, and reuse its payload for the rest of the session; do not call it again.
    ConnectorOAuth
  • Change how much memory an app's managed database gets. Call this when the database is slow or out of memory. db_ram_mb must be one of the sizes get_resource_usage reports under db_ram.steps_mb and fit your database-RAM pool. WARNING: the database restarts briefly to apply the new size, so the app loses its database connection for a few seconds. Only works if the app has a managed database.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables MySQL database analysis through natural language, including schema exploration, query execution, performance analysis, and ER diagram generation via the Model Context Protocol.
    MIT

Matching MCP Connectors

  • MobilityData's open catalogue of public-transport feeds — ~4,500 GTFS schedule feeds and ~1,900…

  • Historical football results, draws and no-draw streaks. 11 read-only tools, 6 need no API key.

  • Initializes a Blockscout MCP session: returns server reference data, the `blockscout-analysis` skill pointer, and the URI resolution rule. Call this tool exactly once per session, before any other tool, and reuse its payload for the rest of the session; do not call it again.
    ConnectorNo auth
  • Get multiple Instagram posts by IDs (1-50 IDs per request). Returns results directly. Returns only found posts, omitting not-found IDs for flexibility. First searches database, then external API for missing/stale data in parallel. Use when you have multiple exact post IDs. NOT for search - use getInstagramPostsByKeywords. PERFORMANCE: Much more efficient than multiple single-ID calls. Batches database queries and parallelizes API calls. IMPORTANT: postIds must be in strong_id format (e.g., "3606450040306139062_4836333238") - use the full "id" value from other Instagram tools, NOT just the media_id. To find a post from an Instagram URL (e.g., instagram.com/p/ABC123/), extract the shortcode from the URL path and use getInstagramPostsByKeywords to search, or ask the user for the post ID. Optional fields parameter for performance: ["id", "caption", "likeCount"]. Returns: results array with id, caption, userId, username, createdAtDate, engagement metrics, count, dataSource. This is a safe, read-only tool for analyzing searchable information.
    ConnectorOAuth
  • Call after uploading the file(s) returned by update_data_spec — kicks off AI analysis and waits until the spec reaches "ready" or "failed". If it returns before that (timedOut: true), do NOT call this tool again just to keep checking — that re-attempts starting analysis. Poll with get_status (specId) instead until it reaches a terminal status.
    ConnectorOAuth
  • Filter the how-to index by analysis family, tool, vertical, and/or a case-insensitive text query against title, analysis name, intro, problem statement, and step operations (with practitioner-synonym coverage, e.g. attrition/turnover/churn, logistic regression/classifier, power bi/dax, diversity/simpson/blau). All filters are optional and combine with AND; call with no arguments to get every page (same as list_howto_pages).
    ConnectorNo auth
  • Search FDA 510(k) premarket clearance submissions — 175,000+ cleared medical devices. Returns k_number, device name, applicant, decision (SESE=cleared), decision date, product code, advisory committee specialty, and clearance type (Traditional/Special/Abbreviated). Filter by device name, k-number, applicant, or product code. A 510(k) clearance means FDA determined the device is substantially equivalent to a legally marketed predicate device. Useful for market research, competitive analysis, and regulatory pathway planning. Source: FDA CDRH 510(k) database, US public domain.
    ConnectorNo auth
  • Start a billed analysis proposing database keys, SQL types, indexes and relationship ownership on a linked schema. Requires editor. Registration already starts the initial pass; use this after relevant edits. Incremental scope covers new properties or changed JSON types/multilingual flags; an empty scope does not rerun unchanged fields. Returns job_id: poll get_job_status and inspect get_schema's working copy. Correct proposals with property tools, then publish_schema to ship changes. Entity-level indexes and ownership choices: enricher://docs/database-sync.
    ConnectorOAuth
  • Verify a factual claim against specific public evidence URLs before an agent repeats it or acts on it. The tool checks whether supplied keywords appear in each fetched source and reports per-source evidence. It does not perform open-ended search, semantic contradiction analysis, or prove a claim true when a page is silent; choose direct evidence URLs and interpret the result as a support signal. Fetched pages are cached for 5 minutes.
    ConnectorNo auth
  • Search Cochrane systematic reviews via PubMed. Finds Cochrane Database of Systematic Reviews articles matching your query. Returns PubMed IDs, titles, and publication dates. Use get_review_detail with a PMID to get the full abstract. Args: query: Search terms for finding reviews (e.g. 'diabetes exercise', 'hypertension treatment', 'childhood vaccination safety'). limit: Maximum number of results to return (default 20, max 100).
    ConnectorNo auth
  • Deletes a managed Postgres database and its underlying VM. Pass the numeric database id from list_databases. This cannot be undone.
    Connector
    Destructive
    No auth
  • Search Sponsorable's podcast-sponsorship database for brands that sponsor podcasts — the deep-research/Responses-API compatibility interface, paired with fetch. Matches sponsor names and domains and returns citable documents; pass a result's id to fetch for the full profile. For filtered or paginated search (category, industry, recency), use search_sponsors instead.
    ConnectorNo auth
  • Title-substring card search within one project (kanban board and backlog), matching the product's in-project live card search exactly (database case-insensitive substring on the card title only — descriptions and comments are not searched; use the search tool for full-text search across all content types), ordered newest-created first. Returns action-sufficient card summaries (uid, title, list placement + position, epic, labels, assignees, reporter, due date); a query with no matches returns an empty cards array, not an error. Paginate with limit (default 50, max 100) and offset; total_count is the full match count.
    ConnectorNo auth
  • Enrich one entity against exactly one of schema_id or target_schema, returning structured output, record_id, costs and any database outcome. Read get_schema's input_contract first (published version when linked); never invent preserve values. Models may be omitted for auto selection. Generation is billed. Two or more models fuse only when all succeed: check failed_models before reporting success. A failed leg prevents automatic fusion and database admission. classification_warning returns success=false, error_code and classification; bypass only after user confirmation. Database sync defaults on: report database.status and database_warning, including partial writes or overwrites; admission is not proof of replica delivery. Recovery and fusion: enricher://docs/enrichment-and-fusion. This tool does not expose web-search activation.
    ConnectorOAuth
  • Check server connectivity, authentication status, and database size. When to use: First tool call to verify MCP connection and auth state before collection operations. Examples: - `status()` - check if server is operational, see quote_count, and current auth state
    ConnectorNo auth
  • Open-ended crypto and DeFi analysis from Einstein's full research stack — use this when no more specific tool fits, or when the question spans several domains. Returns a written analysis grounded in live on-chain and market data. [Paid: $1.00 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]
    ConnectorNo auth
  • Search consumer complaints filed with NHTSA about vehicles. Returns incident details including crash/fire flags, injuries, deaths, affected components, and complaint summary. Covers US vehicles from ~1995 to present. Critical for safety research and product liability analysis (NHTSA)
    ConnectorNo auth