{
  "listings": [
    {
      "slug": "agentvfs",
      "name": "Mirage (AgentVFS)",
      "company": "Strukto.AI",
      "grade": "B",
      "fit": "yes",
      "why": "PostgresVFS mounts read-only with a schemas allowlist; each table has schema.json (types, keys, indexes) and semantic.json, and head or tail on rows.jsonl asks SQL for only those rows, under row and byte caps.",
      "source": "https://docs.mirage.strukto.ai/python/vfs/postgres.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/agentvfs"
    },
    {
      "slug": "clickhouse-mcp-server",
      "name": "ClickHouse MCP Server",
      "company": "ClickHouse, Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "list_tables takes like filters, page_size and page tokens, and include_detailed_columns=false trims output; read-only is enforced server-side with readonly=1 by default. The 100+ table crash in #25 led to the pagination now documented.",
      "source": "https://raw.githubusercontent.com/ClickHouse/mcp-clickhouse/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/clickhouse-mcp-server"
    },
    {
      "slug": "dbhub",
      "name": "DBHub",
      "company": "Bytebase",
      "grade": "BB",
      "fit": "yes",
      "why": "search_objects finds tables by pattern at names, summary or full detail with a limit; read-only is enforced by a keyword allow-list plus the engine's read-only transaction. Two accounts use it for schema checks before writing code.",
      "source": "https://dbhub.ai/tools/search-objects.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/dbhub"
    },
    {
      "slug": "mcp-toolbox-databases",
      "name": "MCP Toolbox for Databases",
      "company": "Google LLC",
      "grade": "A",
      "fit": "yes",
      "why": "postgres-list-tables takes table_names and a simple or detailed output_format, so one table is one call; read-only sources lock the session at engine level and prune write tools from tools/list.",
      "source": "https://mcp-toolbox.dev/integrations/postgres/tools/postgres-list-tables/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mcp-toolbox-databases"
    },
    {
      "slug": "mongodb-mcp",
      "name": "MongoDB MCP Server",
      "company": "MongoDB, Inc.",
      "grade": "A",
      "fit": "yes",
      "why": "list-collections and collection-schema describe collections; --readOnly leaves only read, connect and metadata tools registered; find and aggregate stop at 100 documents by default; --disabledTools atlas trims the list.",
      "source": "https://raw.githubusercontent.com/mongodb-js/mongodb-mcp-server/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mongodb-mcp"
    },
    {
      "slug": "neon-mcp",
      "name": "Neon MCP Server",
      "company": "Neon, LLC (subsidiary of Databricks, Inc.)",
      "grade": "BB",
      "fit": "yes",
      "why": "get_database_tables and describe_table_schema under ?category=schema; ?readonly=true disables writes; run_sql returns 100 rows by default and says when it cut a result; roleName makes grants decide what is read.",
      "source": "https://neon.com/docs/ai/neon-mcp-server.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/neon-mcp"
    },
    {
      "slug": "supabase-mcp",
      "name": "Supabase API + MCP",
      "company": "Supabase Pte. Ltd.",
      "grade": "BB",
      "fit": "yes",
      "why": "list_tables under ?read_only=true\u0026project_ref=...\u0026functions=database,docs, which drops mutating tools; several accounts use it this way to check schemas and permissions before writing code.",
      "source": "https://supabase.com/mcp",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/supabase-mcp"
    },
    {
      "slug": "obsessiondb",
      "name": "ObsessionDB",
      "company": "Kellerkind UG (haftungsbeschränkt)",
      "grade": "F",
      "fit": "caveat",
      "why": "No schema tool; the agent reads system tables or DESCRIBE through run_sql. The workbench:query scope runs any SQL and no read-only mode is documented, so nothing stops a write reaching the database.",
      "source": "https://obsessiondb.com/docs/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/obsessiondb"
    },
    {
      "slug": "planetscale-mcp",
      "name": "PlanetScale MCP Server",
      "company": "PlanetScale, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "execute_read_query runs under a read-only database role with short-lived credentials and a 50-second cancel, but returns every row with no cap, and the schema tools sit in the closed, generated part of the server that could not be read.",
      "source": "https://raw.githubusercontent.com/planetscale/mcp-server/main/src/tools/execute-read-query.ts",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/planetscale-mcp"
    },
    {
      "slug": "postgres-mcp-pro",
      "name": "Postgres MCP Pro",
      "company": "Crystal Corp.",
      "grade": "F",
      "fit": "caveat",
      "why": "list_schemas, list_objects and get_object_details find one table's columns, and restricted mode runs read-only transactions, but #237 (open) reports 0.1.1 to 0.3.0 failing to install after an upstream change, and unrestricted is every README example's default.",
      "source": "https://raw.githubusercontent.com/crystaldba/postgres-mcp/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/postgres-mcp-pro"
    },
    {
      "slug": "redis-mcp",
      "name": "Redis MCP",
      "company": "Redis Ltd.",
      "grade": "C",
      "fit": "caveat",
      "why": "Keys, hashes, JSON and index info can be inspected, but the server has no read-only switch: write and delete tools stay listed, and the README's answer is a read-only Redis ACL user.",
      "source": "https://raw.githubusercontent.com/redis/mcp-redis/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/redis-mcp"
    },
    {
      "slug": "snowflake-managed",
      "name": "Snowflake-managed MCP server",
      "company": "Snowflake Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "A SYSTEM_EXECUTE_SQL tool can read information_schema under the caller's role, but there is no schema tool, and an administrator must first create the MCP server object and an OAuth security integration.",
      "source": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-agents-mcp",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/snowflake-managed"
    },
    {
      "slug": "coinmarketcap-x402-api",
      "name": "CoinMarketCap x402 API",
      "company": "CoinMarketCap",
      "grade": "BB",
      "fit": "no",
      "why": "A paid crypto market-data API (quotes, DEX search) with an x402 MCP endpoint; it exposes no schema of the person's database.",
      "source": "https://coinmarketcap.com/api/documentation/ai-agent-hub/x402",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/coinmarketcap-x402-api"
    },
    {
      "slug": "filesystem-reference-server",
      "name": "Filesystem (MCP reference server)",
      "company": "Model Context Protocol, a Series of LF Projects, LLC",
      "grade": "B",
      "fit": "no",
      "why": "File tools only; no database connection.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/filesystem-reference-server"
    },
    {
      "slug": "memory-reference-server",
      "name": "Memory (MCP reference server)",
      "company": "Model Context Protocol, a Series of LF Projects, LLC",
      "grade": "B",
      "fit": "no",
      "why": "A knowledge-graph file store; no database schema or SQL.",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/memory-reference-server"
    },
    {
      "slug": "nansen-x402-api",
      "name": "Nansen x402 API",
      "company": "Nansen",
      "grade": "B",
      "fit": "no",
      "why": "A paid on-chain analytics API (wallets, Smart Money, token flows); it exposes no schema of the person's database.",
      "source": "https://docs.nansen.ai/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nansen-x402-api"
    },
    {
      "slug": "reqres-mcp",
      "name": "ReqRes MCP server",
      "company": "ReqRes",
      "grade": "D",
      "fit": "no",
      "why": "Works on its own hosted collections, not the repository's database.",
      "source": "https://reqres.in/mcp",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/reqres-mcp"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 12,
    "after": [
      "code.ticket-to-pr"
    ],
    "area": "developer",
    "asks": [
      "what columns does the orders table have",
      "check the schema before you write the migration",
      "does this user have the right role in the database",
      "verify this query returns what the feature expects"
    ],
    "before": [
      "code.understand-codebase"
    ],
    "blockers": [
      "tool list too large for the client (Cursor sends 40 tools)",
      "server fails to start on a fresh install after an upstream dependency change",
      "schema listing crashes on 100+ tables"
    ],
    "capabilities": [
      "db.sql",
      "db.document"
    ],
    "category": "data",
    "categoryName": "Databases \u0026 files",
    "checked": "2026-11-15",
    "companies": {
      "fit": 7,
      "fitWithLimit": 5,
      "tagged": 15
    },
    "competition": "crowded",
    "fits": [
      "agentvfs",
      "clickhouse-mcp-server",
      "dbhub",
      "mcp-toolbox-databases",
      "mongodb-mcp",
      "neon-mcp",
      "supabase-mcp"
    ],
    "fitsWithLimit": [
      "obsessiondb",
      "planetscale-mcp",
      "postgres-mcp-pro",
      "redis-mcp",
      "snowflake-managed"
    ],
    "id": "data.schema-check",
    "listings": {
      "caveat": 5,
      "no": 5,
      "notRead": 0,
      "tagged": 15,
      "unchecked": 0,
      "yes": 7
    },
    "name": "Check the schema or data while writing code",
    "status": "draft",
    "success": "The agent names the tables and columns it needs from the live schema, runs at most a few bounded SELECT or find calls, and writes code that matches them, with no write statement reaching the database. Measured: the schema lookup for one table takes no more than two calls and under 5,000 tokens.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/data.schema-check.json",
    "weight": 22,
    "weightBasis": "12 of 52 accounts; the most common job in the DBHub use-case thread and the Supabase MCP comments on Hacker News"
  }
}
