Connect Claude to PostgreSQL

Inspect the schema of a PostgreSQL database. Toolspoke puts 12 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Sandboxed CLI
Authentication: Connection URL
Actions exposed: 12
Cost per call (typical): 5 credits
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install PostgreSQL
Open the marketplace in your workspace, add PostgreSQL to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with connection url. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. PostgreSQL shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What PostgreSQL asks for

Connection URL. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Connection URLRequired: Use a read-only role where possible. Append ?sslmode=require for managed providers.; postgresql://user:[email protected]:5432/mydb

What Claude can do in PostgreSQL

12 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 12Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

server_info
Report the PostgreSQL version, current database and role, database size and timezone. Call this first to confirm the connection works.
list_schemas
List the non-system schemas in the database with their owner and table count. Use it to find where the application's tables live before calling list_tables.
list_tables
List tables (and optionally views) with their kind, planner row estimate, total size on disk and comment. The row counts are estimates from the planner statistics, not exact counts.
list_tables_and_views
List tables, views and materialised views with their kind, planner row estimate, total size on disk and comment. Use list_tables when you only want real tables.
describe_table
Describe one table or view: every column with its position, type, nullability, default, primary-key membership and comment. Use this before writing a query against an unfamiliar table.
list_indexes
List indexes with their definition, uniqueness, size and how many times the planner has used them. Unused indexes on large tables are the usual thing to look for.
list_foreign_keys
List foreign-key constraints and what they reference, so you can work out how tables join before writing a query.
table_sizes
List the largest tables by total size on disk, split into heap and index bytes with a planner row estimate. Use it to find what is filling the database.
list_extensions
List installed extensions with their version and schema, for example pgvector, postgis or pg_stat_statements.
run_query
Run one read-only SQL query and return the rows. Only a single SELECT, WITH, TABLE or VALUES statement is accepted - no semicolon-separated statements, no INSERT/UPDATE/DELETE/DDL - and the connection is opened in a read-only transaction with a 15 second statement timeout. Results are always capped by `limit`.
explain_query
Return the PostgreSQL execution plan for a read-only query as JSON. Set `analyze` to actually run the query and get real timings and row counts; leave it off for a plan-only estimate. Same read-only restrictions as run_query.
list_activity
List the current sessions on this database, oldest query first, with state, wait event and a truncated query text. Use it to find long-running or blocked queries. Read-only - it cannot cancel anything.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 12 actions above are the whole of it. A call to any other name is refused before it reaches PostgreSQL rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It only reads: Every action here reads. Nothing this connector can do changes anything in PostgreSQL.
It reaches no further than your credential: Toolspoke holds no access to PostgreSQL of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from PostgreSQL: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in PostgreSQL. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around PostgreSQL's own rate limits. A call that PostgreSQL refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in PostgreSQL?

12 named actions: 12 that only read. They include server_info, list_schemas and list_tables. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the PostgreSQL connector need?

Connection URL. The connector asks for connection url. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the PostgreSQL connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 12 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the PostgreSQL connector not do?

The 12 actions above are the whole of it. A call to any other name is refused before it reaches PostgreSQL rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in PostgreSQL. Toolspoke holds no access to PostgreSQL of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in PostgreSQL. An agent has to ask. Toolspoke does not retry, queue or back off around PostgreSQL's own rate limits. A call that PostgreSQL refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches PostgreSQL's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls PostgreSQL?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More database connectors

Browse all of them