Kaiva Postgres MCP

ai.kaivPublished by kaiv.aiv0.1.1Updated Oct 26, 2026

Read-only PostgreSQL MCP server. Drop-in replacement for the archived server-postgres.

The publisher's own server: Kaiva Bridge

VerifiedSTDIODesktop onlyDatabasesData & Analytics

Overview

AI-generated overview

Read-only PostgreSQL MCP server that lets an assistant run single read-only SQL statements and inspect table schemas.

What you can do
  • Run one read-only SQL statement (SELECT, WITH, VALUES, TABLE, SHOW or EXPLAIN) and get rows back as JSON
  • List the tables and views the login can read, with type, estimated row count and comment
  • Describe a table's columns, primary key, unique and foreign keys, referencing tables and indexes
  • Expose each table's columns as resources, as the archived server-postgres did
When to use it
Use it when an assistant should answer questions from a PostgreSQL database without any risk of writing to it, or when replacing the archived server-postgres with a maintained equivalent that keeps the same query tool and schema resources.
Requirements
Runs locally over stdio via the npm package @kaiva/postgres-mcp (npx or Docker image). Needs a PostgreSQL connection URL, given as the first argument or in DATABASE_URL, with TLS options such as sslmode in the URL. A read-only login is recommended. Desktop client only.
Before you install
Anything the login can read, the assistant can read, including system catalogs and password hashes with a superuser login, so use a login that sees only intended tables. The refused-function list is a second guard, not a sandbox: views, foreign tables or functions already defined in the database can still reach files when read as a superuser. A superuser login on a non-local database is refused unless --allow-superuser is set. The README also points to a hosted bridge service that requires the…

Installation

In SourceWeft

  1. Open Kaiva Postgres MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Kaiva Postgres MCP

The Postgres MCP server that stays read-only. A drop-in replacement for the archived @modelcontextprotocol/server-postgres.

Switch in one line

Where your AI client starts the archived server today:

json
{  "mcpServers": {    "postgres": {      "command": "npx",      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://localhost/mydb"]    }  }}

change the package name:

json
      "args": ["-y", "@kaiva/postgres-mcp", "postgresql://localhost/mydb"]

In Claude Code:

sh
claude mcp add postgres -- npx -y @kaiva/postgres-mcp postgresql://localhost/mydb

The query tool, its sql input and the table schema resources are the same, so nothing else changes.

Other ways in, with DATABASE_URL set in your environment:

  • Claude Code plugin: /plugin install postgres-mcp --marketplace ai-kaiva/postgres-mcp
  • Gemini CLI extension: gemini extensions install https://github.com/ai-kaiva/postgres-mcp, then gemini extensions config kaiva-postgres-mcp to enter the database URL
  • Docker: docker run -i --rm -e DATABASE_URL ghcr.io/ai-kaiva/postgres-mcp once the image is published

Why switch

The archived server is no longer maintained: Anthropic archived it in 2025 as a reference example rather than production software, and npm marks it "Package no longer supported". It runs whatever text it is given inside BEGIN TRANSACTION READ ONLY, and that is not enough:

  • COMMIT; DROP SCHEMA public CASCADE ends the read-only transaction and drops the schema (reported by Datadog Security Labs in August 2025; the fix never reached npm, where 0.6.2 is still the latest version).
  • With a superuser login, which is what most local and Docker installs start with, one statement can run a shell command on the database server: PostgreSQL runs COPY ... TO PROGRAM inside a read-only transaction.

We checked both against version 0.6.2 on PostgreSQL 14: both ran. Kaiva Postgres MCP refuses both.

Archived 0.6.2Kaiva Postgres MCP
A second statement after COMMITRunsRefused: one statement per call, and PostgreSQL itself refuses a second
COPY ... TO PROGRAM, server file reads, dblinkRun, if the login allowsRefused
Time limitNone15 seconds per statement, 3 seconds waiting for a lock
Rows returnedAll of themThe first 1,000, and it says so
Superuser loginUsed as givenWarning on this machine; refused for a database on another machine unless you allow it
Tables listedpublic schema onlyEvery schema
Dates and timestampsTurned into JavaScript dates, which can shift a date to the day beforeExactly as PostgreSQL prints them
ErrorsReturned as protocol errorsReturned to the AI with what to fix
MaintainedNoYes

Tools

  • query: run one read-only SQL statement (SELECT, WITH, VALUES, TABLE, SHOW or EXPLAIN) and get the rows as JSON.
  • list_tables: the tables and views this login can read, with type, estimated row count and comment.
  • describe_table: one table's columns, primary key, unique and foreign keys, the tables that reference it, and its indexes.

Resources: each table's columns, as the archived server listed them.

How read-only is enforced

On every call:

  1. The SQL is checked before it is sent: one statement, starting with SELECT, WITH, VALUES, TABLE, SHOW or EXPLAIN, calling no function that reaches past the transaction (dblink, server file functions, lo_import and lo_export, pg_terminate_backend, advisory locks, and functions that run SQL given to them as text).
  2. It runs alone, through PostgreSQL's extended query protocol, which refuses a second statement, inside a READ ONLY transaction with a statement time limit and a lock time limit.
  3. The transaction is always rolled back, and DISCARD ALL resets the session, so nothing a statement sets up outlives it.

Only the first 1,000 rows are fetched from the database (one more is read, to know whether more exist), so a query over a large table returns quickly.

Use a login that can only read

The strongest guard is a login that cannot write. Run this once as an administrator, then put mcp_readonly in the connection URL:

sql
CREATE ROLE mcp_readonly LOGIN PASSWORD 'choose-a-password';GRANT CONNECT ON DATABASE mydb TO mcp_readonly;GRANT pg_read_all_data TO mcp_readonly;  -- PostgreSQL 14 and laterALTER ROLE mcp_readonly SET default_transaction_read_only = on;

To see what a login can do:

sh
npx -y @kaiva/postgres-mcp postgresql://mcp_readonly:...@localhost/mydb --check

Options

OptionDefault
--max-rows <n>1000Rows returned per query, 1 to 10000
--timeout <seconds>15Time limit per statement, 1 to 300
--allow-superuseroffAllow a superuser login on a database on another machine. In Docker Compose the database is another container, so this applies there too; a read-only login is the better answer
--checkConnect once, report what the login can do, and exit

Give the connection URL as the first argument, or set DATABASE_URL. TLS settings go in the URL (sslmode, sslrootcert), as with psql.

What it does not protect

  • Anything the login can read, the AI can read: tables, views and foreign tables, and with a superuser the system catalogs too (pg_authid holds password hashes). Use a login that sees only the tables you mean to share.
  • The refused-function list is a second guard, not a sandbox. It sees the SQL the AI sends, not what a view, a foreign table (file_fdw) or a function already defined in your database does when it is read. With a superuser login such an object can still read a file on the database server. With a login that can only read, PostgreSQL itself refuses (checked: a view over pg_read_file reads the file as a superuser and is refused as a read-only login).
  • "This machine" means localhost, 127.x, ::1, a Unix socket, *.localhost and host.docker.internal (the Docker host). Anywhere else, Docker Compose service names and private network addresses included, a superuser is refused unless --allow-superuser is given.

In Claude.ai, ChatGPT or for your team

This package runs on your machine. To use the same database from Claude.ai or ChatGPT, or share it with your team behind sign-in, Kaiva Bridge serves it as a managed MCP server. In a project folder whose .env holds DATABASE_URL:

sh
npx @kaiva/bridge push mydb --db

Your database must be reachable from the internet. https://kaiv.ai/bridge?utm_source=postgres-mcp&utm_medium=readme

License

MIT

Source: README.md at commit bcb5e90

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the server did not start.

Version history

2
  1. v0.1.1LatestOct 21, 2026
  2. v0.1.0Oct 19, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Kaiv integrations