[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-mcp-database-connectors-es":3,"seo:pack:mcp-database-connectors:es":91},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":90},"mcp-database-connectors","🗃️","#0891B2","new","Nuevo · esta semana","Pack de Conectores MCP para Bases de Datos","Diez servidores MCP que dan a tu agente IA acceso seguro a Postgres, MySQL, MongoDB, Redis y SQLite — cada uno con modo read-only, introspección de esquema y trazabilidad, para que el agente deje de inventar columnas y de borrar tu tabla de producción.",[16,28,35,42,49,56,62,69,76,83],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3283,"216cb667-d5ae-5400-99d5-63dd528e1690","postgres-mcp-pro-index-tuning-safe-sql-tools","Postgres MCP Pro — Index Tuning + Safe SQL Tools","Postgres MCP Pro is an MCP server for PostgreSQL that runs safe SQL, explains plans, and recommends indexes so agents can tune databases faster.","MCP Hub",78,0,"en","mcp","MCP",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":22,"view_count":34,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3284,"e3c6ca46-f9f3-5f60-8ff3-7316792032f3","pgedge-postgres-mcp-read-only-by-default-web-ui","pgEdge Postgres MCP — Read-Only by Default + Web UI","pgEdge Postgres MCP is a Go MCP server for Postgres with read-only defaults, optional HTTP auth, and a web UI for database exploration and diagnostics.",81,{"id":36,"uuid":37,"slug":38,"title":39,"description":40,"author_name":22,"view_count":41,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3559,"0b7eef82-ddb4-52b1-93a3-d64a27bfc5b9","dryrun-offline-postgresql-mcp-no-db-creds","DryRun — Offline PostgreSQL MCP (No DB Creds)","DryRun snapshots your PostgreSQL schema once and provides offline linting plus migration\u002Fquery checks via CLI + MCP, without sharing prod credentials.",10,{"id":43,"uuid":44,"slug":45,"title":46,"description":47,"author_name":22,"view_count":48,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3363,"2c4d8def-3374-5876-87e9-73d83580f5f8","mcp-server-mysql-read-only-mysql-mcp-for-claude-code","mcp-server-mysql — Read-Only MySQL MCP for Claude Code","mcp-server-mysql is an MCP server for Claude Code that connects to MySQL (optionally via SSH tunnels) so agents can inspect schemas and run read-only SQL.",68,{"id":50,"uuid":51,"slug":52,"title":53,"description":54,"author_name":22,"view_count":55,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3827,"f7c6c41e-d6aa-5f02-931d-1945b1bd7caa","mysql-mcp-server-secure-mysql-tools-via-mcp","MySQL MCP Server — Secure MySQL Tools via MCP","mysql_mcp_server is an MCP server for MySQL with pip install and Smithery client setup; expose DB actions to Claude Code safely (1,251★).",75,{"id":57,"uuid":58,"slug":59,"title":60,"description":61,"author_name":22,"view_count":55,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3285,"060ccb08-f4b6-5e96-ad28-3fc2cc23bd44","mongodb-mcp-server-npx-read-only-safety-by-default","MongoDB MCP Server — npx + Read-Only Safety by Default","MongoDB MCP Server exposes MongoDB queries and optional Atlas admin tools to MCP clients via npx or Docker, with a read-only mode that reduces risk.",{"id":63,"uuid":64,"slug":65,"title":66,"description":67,"author_name":22,"view_count":68,"vote_count":24,"lang_type":25,"type":26,"type_label":27},506,"31218ce0-3c2e-4186-9d68-c7606380c905","redis-mcp-server-official-redis-ai-agents-31218ce0","Redis MCP Server — Official Redis for AI Agents","Official Redis MCP server enabling AI agents to manage Redis data via natural language. Supports strings, hashes, lists, sets, streams, JSON, pub\u002Fsub, and vector search. MIT license.",127,{"id":70,"uuid":71,"slug":72,"title":73,"description":74,"author_name":22,"view_count":75,"vote_count":24,"lang_type":25,"type":26,"type_label":27},753,"f67139b3-1666-4c8a-93d9-29c9c29e6ab2","sqlite-mcp-local-database-ai-agents-f67139b3","Sqlite MCP — Local Database for AI Agents","Official MCP server for SQLite databases. Let Claude Code query, analyze, and modify local SQLite databases through natural language. Zero-config, instant setup.",123,{"id":77,"uuid":78,"slug":79,"title":80,"description":81,"author_name":22,"view_count":82,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3716,"92258aef-329c-5d6b-b4b9-3f9784b23ee0","universal-db-mcp-17-databases-read-only-default","Universal DB MCP — 17 Databases, Read-Only Default","Universal DB MCP is a multi-DB MCP connector (stdio\u002Fhttp) with read-only default and caching; verified 782★ and documents 25x–100x speedups in README.",92,{"id":84,"uuid":85,"slug":86,"title":87,"description":88,"author_name":22,"view_count":89,"vote_count":24,"lang_type":25,"type":26,"type_label":27},203,"a3c39721-f393-4d77-a408-a32c721488e3","genai-toolbox-mcp-server-databases-google-a3c39721","GenAI Toolbox — MCP Server for Databases by Google","Open-source MCP server for databases by Google. Connect AI agents to PostgreSQL, MySQL, Cloud SQL, AlloyDB, and Spanner with built-in auth, connection pooling, and safety. 13K+ stars.",181,"tokrepo install pack\u002Fmcp-database-connectors",{"pageType":92,"pageKey":8,"locale":25,"title":93,"metaDescription":94,"h1":95,"tldr":96,"bodyMarkdown":97,"faq":98,"schema":114,"internalLinks":122,"citations":135,"wordCount":148,"generatedAt":149},"pack","MCP Database Connectors: 10 servers for Postgres, MySQL, Mongo, Redis, SQLite","Ten MCP database connectors with read-only defaults, schema introspection, and audit trails — so your AI agent can query Postgres, MySQL, MongoDB, Redis and SQLite without nuking prod.","MCP Database Connectors Pack","Ten MCP servers — one per database, plus two universal routers and one offline dry-run — that give an AI agent safe query access. Read-only by default, schema-aware, and audit-logged. Install once, point at any DSN, watch the agent stop guessing column names.","## What's in this pack\n\nThis is the **broader database MCP pack**. Where [Postgres for AI Agents](\u002Fen\u002Fpacks\u002Fpostgres-for-agents) goes deep on one engine, this one cuts across all five databases an average backend touches — Postgres, MySQL, MongoDB, Redis, SQLite — plus two universal routers and a credential-free dry-run server for the truly paranoid.\n\n| # | Server | Engine | Safety surface |\n|---|---|---|---|\n| 1 | Postgres MCP Pro | Postgres | Index advice, EXPLAIN, safe SQL gate |\n| 2 | pgEdge Postgres MCP | Postgres | Read-only default + web UI to audit calls |\n| 3 | DryRun Offline Postgres MCP | Postgres (schema only) | No DB creds, no live connection — parses SQL against a schema file |\n| 4 | mcp-server-mysql | MySQL | Read-only mode tuned for Claude Code |\n| 5 | MySQL MCP Server | MySQL | Capability scoping, query allow-list |\n| 6 | MongoDB MCP Server | MongoDB | `--read-only` flag, npx install |\n| 7 | Redis MCP Server (official) | Redis | Per-command ACL, official Redis Inc. build |\n| 8 | SQLite MCP | SQLite | Local-only, file-path scoping |\n| 9 | Universal DB MCP | 17 engines | Read-only default across every adapter |\n| 10 | GenAI Toolbox (Google) | Postgres \u002F MySQL \u002F Spanner \u002F AlloyDB | OAuth, IAM-aware, production-grade |\n\nFive engines, three safety levels (read-only, capability-scoped, offline), one install command.\n\n## Why a multi-database MCP pack matters\n\nMost teams don't run a single database. The agent that ships features against the user-facing Postgres also needs to read the analytics MySQL, the session Redis, the catalog MongoDB, and the local SQLite the developer is testing against. Wiring each engine into the agent host with its own ad-hoc MCP server is how you end up with five servers, three credential formats, and zero consistent audit trail.\n\nThis pack picks the connectors that get the same things right across engines:\n\n- **Read-only mode is the default.** Every server here exposes a `--read-only` or equivalent capability flag. Write access is opt-in, not opt-out.\n- **Schema introspection is a first-class tool.** The agent calls `list_tables`, `describe_table`, `list_indexes` instead of guessing.\n- **Connection pooling is built in.** No reconnect storms when the agent fires twenty queries during a single reasoning step.\n- **Audit logging is on by default.** Every query the agent runs lands in a structured log you can grep after an incident.\n\nThe outlier is DryRun (#3): it doesn't touch your database at all. You hand it a schema dump and it lets the agent draft SQL, get type-checked, and explain the plan — all without credentials. Useful when the agent is helping a junior engineer write a migration before anyone's allowed near prod.\n\n## Install — pick DB, set read-only, introspect, query, audit\n\nThe five-step rhythm that every server in this pack supports:\n\n```bash\n# 1. Pick the DB you want the agent to see\ntokrepo install pack\u002Fmcp-database-connectors\n# or one at a time:\ntokrepo install postgres-mcp-pro\ntokrepo install mongodb-mcp-server\n\n# 2. Wire it into your host with read-only ON\n# Example for Claude Code (~\u002F.claude\u002Fmcp.json):\n{\n  \"mcpServers\": {\n    \"postgres\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@pgEdge\u002Fpg-mcp\", \"--read-only\"],\n      \"env\": { \"DATABASE_URL\": \"$READONLY_DSN\" }\n    }\n  }\n}\n\n# 3. Ask the agent to introspect FIRST, query SECOND\n#   Prompt: \"list the tables, describe the orders table,\n#            then write a query for last week's revenue.\"\n\n# 4. Query — agent runs the SELECT, you read the result\n\n# 5. Audit — grep the server log\ntail -f ~\u002F.tokrepo\u002Flogs\u002Fpostgres-mcp-pro.log\n```\n\nFor MySQL swap in `mcp-server-mysql`, for Mongo swap in `mongodb-mcp-server`, for Redis swap in the official `redis-mcp-server`. The five steps are identical — the pack's value is that you only learn them once.\n\n## Read-only mode: why every flag matters\n\nA naive write-enabled MCP is the fastest way to turn an LLM hallucination into a production outage. The classic failure mode: agent reasons about an UPDATE, gets the WHERE clause wrong, and rewrites half the table.\n\nEvery server in this pack flips this default. **The agent has to explicitly request write capability, and your host config has to explicitly grant it.** That's a two-step opt-in, which is exactly what you want for anything that can DROP TABLE.\n\nWhen you do need writes — running a seeded migration, populating a test fixture — use a dedicated role (`mcp_writer`) with grants limited to the specific schemas, never the superuser. Combine with a branch (Neon), a clone (pgEdge), or a Docker fixture (everything else) and the blast radius collapses to one throwaway database.\n\n## Common pitfalls\n\n- **Schema dump cost.** `list_tables` on a 500-table production schema can blow the agent's context window. Filter to a single schema or pass an allow-list.\n- **The universal DB MCP isn't free of engine quirks.** It handles 17 databases, but the JSON-column semantics differ between Postgres and MySQL — the agent will sometimes write Postgres-flavored SQL against MySQL. Add a hint to the system prompt.\n- **Redis ACLs are per-command, not per-key.** The official server respects ACLs, but a `KEYS *` is still O(N) — set `--max-scan-keys` or the agent will block the event loop.\n- **MongoDB's `--read-only` blocks writes but not `eval`.** Older Mongo MCPs let the agent run server-side JavaScript. Stick to the post-2026 builds in this pack which strip `$where` and `$function`.\n- **DryRun's schema must stay fresh.** It's offline by design, so it can't notice a column you added yesterday. Re-export the schema as part of CI.\n\n## How this pack relates to the others\n\nIf you only care about Postgres in depth (Neon, Supabase, branching), use [Postgres for AI Agents](\u002Fen\u002Fpacks\u002Fpostgres-for-agents). If you want the broader MCP surface (browser, GitHub, filesystem), use [MCP Server Stack](\u002Fen\u002Fpacks\u002Fmcp-server-stack). Production setups usually run one item from each: a database connector here, the universal MCP toolbox there, and a vector DB for semantic recall.",[99,102,105,108,111],{"q":100,"a":101},"Why not just use one universal database MCP instead of ten?","Universal MCPs (DBHub, GenAI Toolbox, Universal DB MCP) cover the common case beautifully — one server, many DSNs. But every engine has quirks the universal layer flattens out: Postgres's EXPLAIN ANALYZE, Mongo's aggregation pipeline, Redis's ACL semantics. The engine-specific servers in this pack expose those as first-class tools. Use a universal MCP for breadth, an engine-specific one when the agent needs depth.",{"q":103,"a":104},"Is read-only mode actually enforced, or is it just a flag the agent can ignore?","Enforced at the protocol layer. The MCP server only registers `query` and `describe_table` tools when read-only is on — it literally does not expose `insert`, `update`, `delete` to the host. The agent can't call what isn't there. Belt-and-braces: pair with a read-only Postgres role or a Redis ACL that revokes write commands at the DB layer.",{"q":106,"a":107},"Will these work with Claude Code, Cursor, and Codex CLI?","All three plus Cline, Roo Code, Windsurf, GitHub Copilot, and Gemini CLI. MCP is a standard — the TokRepo CLI writes the right config file for whichever host you're running. The same server binary serves every host.",{"q":109,"a":110},"What's the difference vs the Postgres for AI Agents pack?","Postgres for AI Agents goes deep on one engine — five Postgres servers including Neon and Supabase, branch-per-task workflow, RLS gotchas. This pack goes wide — one or two servers per engine across Postgres, MySQL, Mongo, Redis, SQLite. Pick this one if your stack is polyglot, that one if everything is Postgres.",{"q":112,"a":113},"How does the DryRun server help if it can't see live data?","Two ways. First, it lets junior engineers and the agent draft SQL safely — no chance of leaking creds in a screenshot, no chance of an accidental DELETE. Second, it doubles as a CI check: pipe every PR's proposed SQL through DryRun against the production schema dump, and the build fails when a query references a column that doesn't exist.",{"@context":115,"@type":116,"name":95,"description":117,"numberOfItems":41,"publisher":118},"https:\u002F\u002Fschema.org","CollectionPage","Ten MCP servers for safe Postgres, MySQL, MongoDB, Redis and SQLite access from AI agents.",{"@type":119,"name":120,"url":121},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[123,127,131],{"url":124,"anchor":125,"reason":126},"\u002Fen\u002Fpacks\u002Fpostgres-for-agents","Postgres for AI Agents","deep Postgres-only companion (Neon, Supabase, branching)",{"url":128,"anchor":129,"reason":130},"\u002Fen\u002Fpacks\u002Fmcp-server-stack","MCP Server Stack","broader MCP toolbox these connectors fit into",{"url":132,"anchor":133,"reason":134},"\u002Fen\u002Fpacks\u002Fdb-schema-migration","Database Schema + Migration Pack","the schema-design layer that pairs with these connectors",[136,140,144],{"claim":137,"source_name":138,"source_url":139},"Model Context Protocol specification","modelcontextprotocol.io","https:\u002F\u002Fmodelcontextprotocol.io",{"claim":141,"source_name":142,"source_url":143},"Official MongoDB MCP server","mongodb-js\u002Fmongodb-mcp-server","https:\u002F\u002Fgithub.com\u002Fmongodb-js\u002Fmongodb-mcp-server",{"claim":145,"source_name":146,"source_url":147},"Official Redis MCP server","redis\u002Fmcp-redis","https:\u002F\u002Fgithub.com\u002Fredis\u002Fmcp-redis",920,"2026-05-22T13:00:00Z"]