Real-time Firestore schema context for AI coding agents. Stop hallucinating field names.
Real-time Firestore schema context for AI coding agents. Stop hallucinating field names. That is what the lintbase mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Developers are constantly feeding context files to AI tools like Cursor, Windsurf, Copilot Workspace, and Claude Code. If your agent doesn't understand your real database schema, it writes code that fails in production.
The server publishes 14 tools. What each one is for:
Firestore — npx lintbase scan firestore --key ./sa.jsonMongoDB — npx lintbase scan mongodb --uri mongodb+srv://user:pass@cluster.mongodb.net/testRule — What it detectsno-auth-check — Collections readable/writable without authexposed-pii — Email, phone, SSN fields without encryption markersworld-readable — Documents with overly permissive security ruleslarge-collection — Collections with 100k+ docs and high read costunbounded-query — Queries without limit() that scan entire collectionsmissing-index — Filter combinations that fall back to full collection scansdebug-collection — Collections that look like temporary data that was never cleaned uptype-inconsistency — Field stored as different types across documentsmissing-required-field — Field present in 90%+ of docs but absent in someThe server ships on npm as lintbase, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Lintbase's toolset — Firestore, MongoDB, Rule and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Madia333; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Lintbase's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Firestore | npx lintbase scan firestore --key ./sa.json |
| MongoDB | npx lintbase scan mongodb --uri mongodb+srv://user:pass@cluster.mongodb.net/test |
| Rule | What it detects |
| no-auth-check | Collections readable/writable without auth |
| exposed-pii | Email, phone, SSN fields without encryption markers |
| world-readable | Documents with overly permissive security rules |
| large-collection | Collections with 100k+ docs and high read cost |
| unbounded-query | Queries without limit() that scan entire collections |
| missing-index | Filter combinations that fall back to full collection scans |
| debug-collection | Collections that look like temporary data that was never cleaned up |
| type-inconsistency | Field stored as different types across documents |
| missing-required-field | Field present in 90%+ of docs but absent in some |
| nullable-id | Reference fields that are sometimes null |
| deep-nesting | Document fields nested > 3 levels deep |
{
"mcpServers": {
"lintbase": {
"command": "npx",
"args": ["-y", "lintbase"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.