Supabase
Persistence layer with full Postgres access and Row Level Security awareness. Query tables, manage schemas, handle auth users, and work with storage buckets.
“The production-grade database MCP. RLS-aware queries, schema management, and auth user handling make this the standard for agents that need structured persistence.”
INSTALL THIS SERVER
{
"mcpServers": {
"supabase": {
"command": "npx",
"args": ["-y", "@supabase/mcp-server-supabase@latest", "--access-token", "your-token"]
}
}
}
claude mcp add supabase \
--command "npx" \
--args "-y,@supabase/mcp-server-supabase@latest,--access-token,your-token"
18 TOOLS AVAILABLE
OUR ASSESSMENT
- Full Postgres query access with RLS enforcement
- Schema management (create tables, add columns, set up policies)
- Auth user management and storage bucket operations
- Read-only mode available for safe exploration
- Supabase-specific (general Postgres uses the postgres-mcp server)
- Complex RLS policies can produce unexpected query results for agents
Uses Supabase Access Token with project-level scope. RLS policies apply to all queries. Use read-only mode for exploration workflows.
Connecting agents to Postgres with Row Level Security and Supabase ecosystem access
TECHNICAL DETAILS
ADOPTION METRICS
// Reading this2,663 stars on the supabase-community/supabase-mcp repo. 22 commits on main in the last 30 days. Audit (2026-05-03) corrected inflated stored value (4,200 → 2,663).
// Reading thisStrong adoption among teams already on the Supabase platform. Download growth tracks closely with Supabase platform growth.
// Reading this#1 in Database. Globally #5 reflects strong cross-category demand for database access.
SOURCES & VERIFICATION
We don't take any single directory's word for it. Before scoring, we cross-reference 5 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.
The same server, 5 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.
| Source | Their rating | Their star count | Their downloads | Last synced |
|---|---|---|---|---|
| AutomationSwitch This page | 5editorial | 2,663 | 18.6K / wk | MAY 3, 2026 |
| Official MCP Registry | — unrated | 2,100 | unavailable | APR 12, 2026 |
| PulseMCP | 4.3 community | 2,080 | 18.4K / wk | APR 21, 2026 |
| Smithery | 4.5 installs | 2,100 | 22.1K installs | APR 20, 2026 |
| Glama | — unrated | 2,110 | unavailable | APR 18, 2026 |
| MCP.so | 4.2 votes | 2,100 | unavailable | APR 15, 2026 |
// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.
OTHER DATABASE MCP SERVERS
Postgres MCP
Official MCP server for PostgreSQL. Provides read and write access to PostgreSQL databases with schema introspection, query execution, and transaction support. The reference implementation for database MCP servers.
MCP Toolbox for Databases
Google's open-source MCP server for databases. One MCP binary speaks PostgreSQL, MySQL, BigQuery, Spanner, AlloyDB, Cloud SQL, and SQLite. 14,937 GitHub stars and 100 commits on main in the last 30 days. Highest commit cadence in the directory.
ClickHouse MCP
Official ClickHouse MCP server with both ClickHouse Tools (production cluster queries) and chDB Tools (embedded ClickHouse for local analytics). Apache-2.0 with destructive-operation protection: write access is opt-in via configuration.
Redis MCP
Official Redis MCP server with natural-language interface for managing and searching Redis data. EntraID authentication for Azure Managed Redis included; Redis ACL configurable via environment variables. Tool coverage spans strings, lists, hashes, sets, sorted sets, JSON, vectors, and search.
Elasticsearch MCP
Elasticsearch and OpenSearch MCP server with index management, document CRUD, search queries, cluster health, and aggregations. 270 stars and 22 commits on main in the last 30 days.
MindsDB
MindsDB ships native MCP server support as part of the main project (mindsdb/mindsdb, 39,093 stars). Federated query layer over 200+ data sources with built-in MCP endpoint for AI agent access to enterprise data.
DISCUSS YOUR
MCP REQUIREMENTS.
Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.