Compare the open source MySQL MCP servers in 2026: DBHub, mcp-server-mysql, mysql_mcp_server and PlanetScale MCP, on write posture, host neutrality and maintenance.

Top Open Source MySQL MCP Servers in 2026

Our proposed database review workflow: static SQL rules enforce policy, Jev assesses contextual risk, an LLM explains the findings, and a human approves.

Testing Jev on Database Change and Access Workflows

Oracle SQL review tools compared: PLSQL_WARNINGS, SQLcl CODESCAN, dbLinter, SonarQube, SQLFluff, Toad, Flyway, utPLSQL, and where Bytebase's approval gate fits.

Top Oracle SQL Review Tools in 2026

Map key SOC 2 criteria in CC6, CC7, and CC8 to example database access controls and audit evidence, including who can read production data.

Database Access Control for SOC 2: CC6, CC7, and CC8 at the Database

Compare zero-downtime schema migration strategies: native online DDL, expand-and-contract, online schema change tools, and blue-green deployments.

Zero-Downtime Database Schema Migration Strategies

A SQL Server schema migration tool moves a database from one schema version to the next. This guide reviews 8 tools, migration-based and state-based.

Top 8 SQL Server Schema Migration Tools in 2026

Replit's agent wiped a production database during a code freeze, then said rollback was impossible. It wasn't. Every step of that failure maps to a control you can put in place today.

How to Prevent an AI Agent From Dropping Your Production Database

Streaming production to a warehouse and masking in dbt masks for analysts, not operators. Where cleartext survives, and what production masking needs.

Data Masking Architecture: Why the Warehouse Pattern Leaves Production Exposed

SQL Server SQL review tools compared: the built-in SR rules in SQL projects, SqlServer.Rules' 140+ T-SQL checks, SQLFluff, tSQLt, Redgate, and where Bytebase's approval gate fits.

Top SQL Server SQL Review Tools in 2026

A SQL Server schema compare tool diffs two databases and generates the T-SQL to reconcile them. This 2026 guide reviews 8 tools and what each one costs.

Top 8 SQL Server Schema Compare Tools to Diff and Sync Databases in 2026

What the HIPAA Security Rule asks of database access: a name on every session, minimum necessary at the column, emergency access that still gets logged, and an audit trail that can say who read a patient's chart. The controls behind each, what OCR fines, and what the proposed 2027 rule tightens.

Database Access Control for HIPAA: The Security Rule at the Database

I followed Flyway's, Liquibase's, and Bytebase's own recommended quickstarts to a first managed PostgreSQL migration. Two took about half an hour. One took about an hour and a half.

From Zero to First Migration: How Much Setup Do Flyway, Liquibase, and Bytebase Require?

MySQL SQL review tools compared: SQLFluff for style, Skeema for schema-design linting, SOAR for query anti-patterns, and where Bytebase fits as the approval layer.

Top MySQL SQL Review and Lint Tools in 2026

What PCI DSS v4.0.1 asks of database access: least privilege by role, MFA on every CDE session, service accounts treated like humans, masked PANs, and a query-level trail kept for a year. Where each control lives, and where Bytebase stops.

Database Access Control for PCI DSS: Requirements 7, 8, and 10 at the Database

How PostgreSQL evolved from blocking DDL toward concurrent operations, metadata-only changes, and deferred constraint validation.

The Evolution of PostgreSQL Schema Migrations: Less Locking, Less Rewriting, Less Downtime

RDS IAM authentication replaces a stored database password with a 15-minute token. This reference implementation adds the rest of the JIT path: a scoped IAM role, verified identity, a bounded session, approval in Git, and an honest look at the four limits that remain.

Just-in-Time Database Access with AWS RDS IAM Authentication

Four missing primitives: delegation, attenuation, immutable application context, and labels on data. GRANT and RLS are a good policy engine, but nothing trustworthy feeds it when the caller is an AI agent. Oracle and SQL Server solved pieces of this; Postgres has none of it.

What Postgres is Missing for AI Agents

Bytebase and Delphix both mask sensitive data, but at different points: Delphix masks non-production copies, Bytebase masks live production queries.

Bytebase vs. Delphix: a tale of two data masking stories

Comparing HashiCorp Vault, Infisical, Doppler, and 1Password, the vendor-neutral options for database credentials that work across clouds and on-prem.

Best Secrets Manager for Database Credentials in 2026: Vault vs Infisical vs Doppler

On-behalf-of (OBO) is the pattern for AI agents to act with a caller's delegated identity instead of a shared credential. No mainstream database engine carries it the way agents need, and here is why a governance layer in front of the database is where it has to live.

On-Behalf-Of Database Access for AI Agents

Postgres SQL review tools compared: SQLFluff for style, Squawk for migration safety, plpgsql_check and pgTAP, and where Bytebase's rule engine overlaps them with an approval gate attached.

Top Dynamic Data Masking Tools in 2026

Compare direct database CLI access with a governed MCP server across six dimensions: setup, reach, identity, governance, auditability, and workflow fit.

MCP vs. CLI: How an AI Agent Should Reach Your Database

Zero trust for databases extends identity and network controls to SQL statements, query results, data changes, and schema changes.

Zero Trust for Databases: From Access Control to SQL Control

Snowflake and the data warehouses can tag any database object with structured metadata and drive masking from it. Almost no production database can. In the LLM era, that inline, self-contained context is exactly what agents need.

Object Tagging: The AI Feature Almost Every Production Database Skipped

DbUp runs your .NET migrations. Bytebase governs the database: change, access, and compliance in one platform. A practitioner comparison.

Bytebase vs. DbUp: from migration runner to unified governance

Database governance lives upstream, on the production database. Here is how to actually govern the source: reviewed changes, scoped access, codified policy, and audit where the data is born.

How to Govern Data at the Source: A Guide to Upstream Database Governance

Data governance and database governance are four letters apart and constantly conflated. They are different disciplines, owned by different teams, solved by different tools. Here is the dividing line.

Data Governance vs. Database Governance: The Difference Is the Base

PopSQL shuts down on September 1, 2026. Compare Bytebase and PopSQL across query collaboration, supported databases, access control, data masking, audit logging, and pricing before you migrate.

Bytebase vs. PopSQL: a side-by-side comparison for migrating teams

PopSQL shuts down on September 1, 2026. Compare the top PopSQL alternatives for team SQL editing, dashboards, and governed database access before you migrate.

Top PopSQL Alternatives 2026: Where to Migrate Before the Shutdown

The best multi-database MCP servers in 2026. Compare DBHub, Google's MCP Toolbox for Databases, and Bytebase on engine breadth, host neutrality, and governance for connecting AI agents to more than one database. Single-engine Postgres servers are covered in a companion post.

Top 3 Open Source Multi-Database MCP Servers in 2026

The best open source Postgres MCP servers in 2026. Compare Postgres MCP Pro, Supabase MCP, and pgconsole on host neutrality, access model, and governance for connecting AI agents to PostgreSQL. Multi-database MCP servers are covered in a companion post.

Bytebase vs. SchemaHero: a side-by-side comparison for database schema migration

Money software is judged not on whether the feature works, but on what the database can prove eighteen months later. Fintech database governance through three principles: no invented data, no lost data, no trust.

Database Governance for Fintech: Guarding the Ledger

PostgreSQL has no ADD COLUMN ... AFTER. The reason one little number in a system catalog turned a "simple" feature into a decade-long engineering saga, and what you can do about it today.

Why It's So Hard to Add a Column in the Middle of a PostgreSQL Table

What a database MCP server is, what it hands an AI agent, where the credentials live, and why a raw one is fine locally but needs access control against production.

What is a Database MCP Server?

Most database MCP servers hand an agent a connection string and call it a day. The MCP server is the one place access control, masking, approval, and audit either apply to the agent or get walked around.

Governed MCP vs. Raw MCP: How Agents Reach Your Database

AI agents are no longer just reading your database, they are authoring the migrations. The write path is a different risk class, and it needs its own gate.

When the Agent Writes the Migration, Who Approves It?

Generic PAM controls the database connection. Database PAM controls the SQL statement: per-query authorization and approval, SQL review, data masking, and statement-level audit. What the category means and why it exists.

What is Database PAM (Privileged Access Management)?

How to run SQL Server schema migrations safely in production, covering state-based vs migration-based workflows, online index operations, batched backfills, the expand-and-contract pattern, Availability Groups, and CI/CD.

SQL Server Schema Migration and Change Management

CyberArk is a broad privileged access management (PAM) platform. Bytebase is a database-specific PAM for access control, masking, and SQL review. If you already run CyberArk, here is why you still need it for the database.

Bytebase vs. CyberArk: the database vertical in your PAM stack

Database credentials management best practices: store passwords and secrets in one place, rotate on a schedule, and separate the application path from the human path.

Database Credentials Management: Best Practices

The practical ways to audit MySQL activity, from the general query log to audit plugins, binlog CDC, and Bytebase, and where each one falls short.

MySQL Audit Logging Guide

Every critical asset has its system of record, except the database. Bytebase is the one. The standard for database development.

The Standard for Database Development

Dynamic data masking is chosen by access path, not product. Five approaches (engine-native, in-database, application, BI layer, and Bytebase) and which caller each one masks.

How to Implement Dynamic Data Masking: Five Approaches by Access Path

Static vs dynamic data masking, when each applies, how they differ on backups, performance, and reversibility, and when to run both.

Static vs Dynamic Data Masking: When to Use Which

The static data masking tools that produce safe non-production data, Delphix, Tonic.ai, and greenmask compared, plus how to roll your own when no tool fits.

Static Data Masking Tools (and How to Roll Your Own)

Compare BigQuery data masking options: native column-level dynamic data masking (built-in masking rules via policy tags and data policies, Dataplex catalog) and Bytebase fleet-wide masking.

BigQuery Dynamic Data Masking

Compare SQL Server data masking options, native Dynamic Data Masking (five mask types, SQL Server 2022 granular UNMASK) and Bytebase fleet-wide masking.

SQL Server Dynamic Data Masking

Compare Oracle data masking options. Native Data Redaction (five function types via DBMS_REDACT, EXEMPT REDACTION POLICY) and Bytebase fleet-wide masking.

Oracle Dynamic Data Masking

You write a one-line UPDATE against production. Here's the lane that keeps it safe: the four phases, the controls, and what each one prevents.

How to Handle Ad-hoc Database Data Changes?

Notes on the MySQL 9.7 LTS release: Hypergraph Optimizer in Community, JSON Duality View DML, Group Replication observability, and Dynamic Data Masking for Enterprise.

Notes on the MySQL 9.7 LTS release

Most DAC implementations stop at the connection. Real DAC operates at the statement and covers three vectors: machine, human, and AI agent.

What is Database Access Control (DAC)?

How to run dynamic data masking so it survives an audit: mask by role, go column-level, log unmask events, review policy changes in code, and keep environments in sync. Plus a vendor comparison and an end-to-end walkthrough.

Dynamic Data Masking Best Practices

How Bytebase audits the workflow layer: every SQL, schema change, approval, and export tied to a real user identity, with structured exports for any SIEM.

How Bytebase Handles Audit Logging

PostgreSQL 19 features I'm excited about: planner advisor framework, DDL extraction, online REPACK, pg_stat_recovery, parallel autovacuum, sequence sync, and 64-bit MultiXact.

PostgreSQL 19 features I'm excited about

Bytebase is HIPAA-compliant — independent verification that our administrative, physical, and technical safeguards meet the HIPAA Security Rule for handling Protected Health Information.

HIPAA Compliance

PAM governs who can reach a database. Bytebase governs what SQL and schema changes happen once they get there. Where they differ, and why teams use both.

Bytebase vs. PAM: Why Database Teams Need More Than Privileged Access Management

What SOC 2 compliance audits actually want from your database audit log: not 'logging enabled' but evidence your auditor will accept. Lessons from going through our own audit.

SOC 2 Audit Log Requirements: Lessons From Our Own Audit

Bytebase vs. Atlas compared across migration approach, developer interface, supported databases, ORM integration, linting, approval, access control, audit, and pricing. Updated for Atlas v1.3 and Bytebase 3.22.

Bytebase vs. Atlas: a side-by-side comparison for database schema migration

Database access control practices that hold up in a SOC 2 audit: least privilege, separation of duties, just-in-time access, statement-level enforcement, and the common mistakes that get flagged.

Database Access Control (DAC) Best Practices

A practical look at what SOX Section 404 expects from database changes: the four ITGC domains, the six questions auditors actually ask, and how to make compliance evidence a byproduct of your workflow.

Database Change Management for SOX Compliance

TRUNCATE and DELETE both remove rows, but they differ in speed, rollback behavior, and locking. Here is how each one behaves in PostgreSQL, MySQL, and SQL Server, and when to reach for which.

TRUNCATE vs DELETE in SQL: Differences Across PostgreSQL, MySQL, and SQL Server

A practical walk through six database design patterns you will actually meet in production: normalization, star schema, EAV, polymorphic associations, multi-tenancy, and the anti-patterns worth avoiding.

Database Design Patterns Every Developer Should Know

A practical walkthrough of pgvector: installing the extension, storing embeddings, writing similarity queries, building HNSW indexes, and knowing when plain PostgreSQL is enough.

pgvector: How to Add Vector Search to PostgreSQL

How upsert works across MySQL, PostgreSQL, and SQL Server, with the syntax for each, the edge cases worth knowing before you ship, and how upserts interact with migrations.

Upsert in SQL: INSERT ON DUPLICATE KEY vs ON CONFLICT Explained

AI agents need more than DDL. The full database lifecycle codified (schema, dependencies, ownership, history) gives LLMs the context to query correctly.

From Schema as Code to Schema as Context

How to find and fix slow MySQL queries: reading the slow query log, using EXPLAIN, tuning indexes, and rewriting queries, with a worked example for each.

How to Fix Slow MySQL Queries: A Practical Guide

Convex and Supabase are both backend-in-a-box platforms, but built on different foundations. This post compares their architecture, real-time model, data model, schema management, and pricing to help you decide.

Convex vs Supabase: Which Backend Platform Should You Choose?

Blue-green deployment is easy when your servers are stateless. The trouble starts at the database. This guide walks through why database blue-green is hard and how to do it without corrupting your data.

Database Blue-Green Deployment: A Practical Guide

A look at 10 data management tools developers and data engineers actually use in 2026: GUI clients, schema migration, pipelines, and analytics, with pricing for each.

Top 10 Data Management Tools in 2026

How to give AI agents governed access to enterprise data: access control, Dynamic Data Masking, audit logging, and just-in-time grants, applied to a new principal type.

How to Govern AI Agent Database Access

The best SQL editors built exclusively for PostgreSQL: what each one is good at, who it fits, and when a Postgres-only tool beats a multi-database client.

Enterprise Text-to-SQL: Context, Evaluation, and Governance

A practical look at the database deployment tools DevOps teams actually use in 2026 — Flyway, Liquibase, Atlas, pgschema, Octopus Deploy, Harness, DBmaestro and Bytebase — sorted by how each one defines, applies, and coordinates schema changes.

Database Deployment Tools for DevOps Teams in 2026

A walk-through of how renaming a single column can quietly break an analytics pipeline, why it happens, and how schema change detection and notification help you catch it early.

Schema Change Detection and Notification: Why a Simple Column Rename Can Break Your Data Pipeline

How to read a Postgres query plan, spot the common performance problems, and fix them without breaking other queries.

Postgres Query Plan: How to Read and Fix Performance Issues

A walk through every layer of the Postgres permission system that can raise ERROR 42501, why each one fires, and how the behavior differs from MySQL.

The Anatomy of Postgres Permission ERROR 42501

A practical look at Postgres logs: what they record, how the logging collector works, which parameters actually matter in production, and the mistakes that turn logs into expensive noise.

Postgres Logs Explained: A Practical Guide for Production

Postgres 19 widens MultiXactOffset to 64 bits, eliminating the hidden 4 billion member limit that caused catastrophic outages for high-concurrency workloads.

Postgres 19 Feature Preview: 64-bit MultiXactOffset

How to run MySQL schema migrations without blocking queries or causing downtime, covering the MySQL-specific behaviors that bite in production and the tools that work around them.

MySQL Schema Migration Best Practice

Postgres 19 introduces automatic sequence synchronization for logical replication, eliminating manual tracking and making major version upgrades and failover significantly easier.

Postgres 19 Feature Preview: Sequence Synchronization for Logical Replication

What multi-environment database deployment actually involves, the problems teams keep hitting, and the patterns (manual scripts vs GitOps) for handling them.

Database Multi-Environment Deployments - The Challenges and Patterns

A guide to open source sensitive data discovery tools, from NLP libraries like spaCy and Microsoft Presidio to multi-source scanners like Hawk-Eye and full metadata platforms like OpenMetadata.

Top Open Source Sensitive Data Discovery Tools in 2026

Database audit logging really has two layers: the infrastructure layer your cloud provider ships, and the workflow layer you have to build yourself. Here is what each one captures, and why an audit needs both.

Database Audit Logging: Two Layers, One Trail

A practical guide to HITRUST database compliance covering access control, audit logging, change management, and data protection.

Database Compliance for HITRUST: Controls, Risks, and Best Practices

What the "Require Primary Key" SQL review rule checks, the production problems a missing primary key tends to cause, and the SQL to fix tables that don't have one.

Require Primary Key: A SQL Review Rule Explained

What the "Enforce NOT VALID in CHECK" SQL Review rule does, why adding a CHECK constraint can lock your table, and how the two-step NOT VALID approach avoids it.

Enforce NOT VALID in CHECK: A SQL Review Rule Explained

The practical ways to audit a PostgreSQL database, from native logging to triggers, logical replication, pgAudit, and Bytebase, with the trade-offs of each.

Postgres Audit Logging Guide

Learn why CASCADE operations in SQL can lead to catastrophic data loss and how the "Prohibit CASCADE" review rule protects your production database.

Prohibit CASCADE: A SQL Review Rule Explained

A walkthrough of moving each Supabase piece (database, auth, storage, functions, realtime, networking) to its AWS counterpart, with a services-first order that keeps the final database cutover simple.

How to Migrate from Supabase to AWS

Six open-source PostgreSQL backup tools compared for 2026, with the language, license, interface, and best-fit use case for each, plus a note on which ones are still maintained.

What is Enterprise Database Management (EDM)?

A plain explanation of Postgres Transaction ID (XID) wraparound: what causes it, how to check how close you are, and what keeps it from taking your database offline.

Postgres Transaction ID (XID) Wraparound

How a CI/CD pipeline for database schema migration works end-to-end. What it gates, what it leaves outside, and the tools that fit.

How to Build a CI/CD Pipeline for Database Schema Migration

A practical guide to shipping features with PostgreSQL, covering my day-to-day development workflow, the tools I actually use, and real-world examples

How I Ship Features with Postgres

What LGPD means for database operations: how it actually differs from GDPR, what the ANPD sanctions in practice, and the database controls (classification, masking, retention, audit) that hold up.

Database Compliance for LGPD: Implications and Best Practices

What a Postgres LATERAL JOIN does, when to reach for one, and the patterns and gotchas you'll run into using it.

What is Postgres LATERAL JOIN?

What MySQL Online DDL actually does, how its three algorithms (INSTANT, INPLACE, and COPY) differ, and the limitations to plan around before you run a schema change in production.

MySQL Online DDL: A Practical Guide

The best open-source Postgres connection poolers in 2026. Compare PgBouncer, Odyssey, PgDoorman, and PgDog — with our pick: PgBouncer if you want free, PgDog if you want a commercial vendor.

Top 4 Open Source Postgres Connection Poolers (2026)


The difference between a primary key and a foreign key comes down to identity versus reference. A **primary key** uniquely identifies each row in a table. A **foreign key** is a column that points at some other table's primary key, which is how you link two tables together.

Think of it like a passport. Your passport number uniquely identifies you, and that is the primary key. When a hotel writes that number on a booking, the booking now refers to you without copying your whole identity, and that is the foreign key. Many bookings can carry the same number, and the number is meaningless unless a real passport with it exists. Referential integrity is just the hotel refusing to file a booking for a passport number that was never issued.

Everything else follows from that one idea. Here is the whole thing at a glance, then the parts that actually matter in practice.

| | Primary key | Foreign key |
| --- | --- | --- |
| What it does | Uniquely identifies each row | Links a row to a row in another table |
| Uniqueness | Values must be unique | Values can, and do, repeat |
| NULL values | Not allowed | Allowed, unless you add `NOT NULL` |
| Per table | At most one | As many as you need |
| Indexing | Created automatically | You usually add it yourself |
| Integrity it enforces | Entity integrity (every row is identifiable) | Referential integrity (no orphaned rows) |

## What a primary key is

A primary key is the column, or set of columns, that uniquely identifies every row. It enforces **entity integrity**, the rule that every row can be told apart from every other. Two things follow. The values are unique, so no two rows share a primary key. And the values are never NULL, because NULL means "unknown" and you cannot identify a row by an unknown value. SQLite is the one that breaks this, letting a NULL sit in a primary key ([a documented quirk](https://sqlite.org/lang_createtable.html), not something to lean on).

Most databases also index the primary key for you, so lookups and joins on it are fast with no extra work.

```sql
CREATE TABLE customers (
    customer_id INT GENERATED ALWAYS AS IDENTITY,  -- MySQL: INT AUTO_INCREMENT
    email VARCHAR(100) NOT NULL,
    first_name VARCHAR(50) NOT NULL,
    last_name VARCHAR(50) NOT NULL,
    PRIMARY KEY (customer_id)
);
```

Here `customer_id` is the primary key. Two customers can share a name, but they can never share a `customer_id`. A primary key can also span more than one column, which is a **composite key**, and that is the right call when no single column identifies a row on its own.

## What a foreign key is

A foreign key is a column, or set of columns, whose values must match a primary key (or a unique key) in another table. It enforces **referential integrity**, so a reference always points at something real and you never get an order that belongs to a customer who does not exist.

```sql
CREATE TABLE orders (
    order_id INT GENERATED ALWAYS AS IDENTITY,
    customer_id INT NOT NULL,
    order_date TIMESTAMPTZ NOT NULL,
    total_amount DECIMAL(10,2) NOT NULL,
    PRIMARY KEY (order_id),
    FOREIGN KEY (customer_id) REFERENCES customers (customer_id)
);
```

`customer_id` in `orders` is a foreign key pointing at `customer_id` in `customers`. Unlike the primary key, it repeats: one customer places many orders, so the same value shows up on many rows. It can also be NULL when the relationship is optional, unless you mark the column `NOT NULL`.

## The differences that bite

The table up top is the easy part. Here is what actually causes production incidents.

**Foreign keys are usually not indexed for you.** If you take one thing from this post, take this. A primary key gets an index automatically. A foreign key does not, at least in PostgreSQL and SQL Server (MySQL's InnoDB is the exception and creates one). Forget to index a foreign key on a large child table and every `DELETE` or `UPDATE` on the parent has to scan the child to check the constraint. On a 40-million-row `orders` table that turns a one-row delete into a full-table scan. So add the index yourself:

```sql
CREATE INDEX idx_orders_customer_id ON orders (customer_id);
```

**NULL and uniqueness are mirror images.** A primary key is unique and non-NULL by definition. A foreign key is neither: its values repeat, and a NULL is allowed and simply means "not related to anything yet."

**Changing a primary key hurts, changing a foreign key does not.** Once rows reference a primary key you cannot casually change or drop it without touching everything that points at it. A foreign key value you can repoint at a different parent any time, as long as that parent row exists.

**Cascade actions live on the foreign key.** You decide what happens to the child rows when the parent changes:

```sql
CREATE TABLE order_items (
    item_id INT GENERATED ALWAYS AS IDENTITY,
    order_id INT NOT NULL,
    product_id INT NOT NULL,
    quantity INT NOT NULL,
    PRIMARY KEY (item_id),
    FOREIGN KEY (order_id) REFERENCES orders (order_id) ON DELETE CASCADE,
    FOREIGN KEY (product_id) REFERENCES products (product_id) ON DELETE RESTRICT
);
```

`ON DELETE CASCADE` removes the line items when their order is deleted. `ON DELETE RESTRICT` blocks deleting a product that orders still reference. Pick deliberately, because `CASCADE` is convenient right up until it deletes more than you intended.

## How they fit together

A primary key gives a row a stable identity. A foreign key borrows that identity to express a relationship. They are two halves of the same mechanism, which the e-commerce [schema](/blog/what-is-database-schema/) below shows.

![er](/content/blog/primary-key-vs-foreign-key/er.webp)

- `customers.customer_id` (primary key) is referenced by `orders.customer_id` (foreign key): one customer, many orders.
- `orders.order_id` is referenced by `order_items.order_id`: one order, many items.
- `products.product_id` is referenced by `order_items.product_id`: one product, many line items.
- `product_categories` is a pure join table: its **composite primary key** is made of two foreign keys, `product_id` and `category_id`, which is the standard way to model a many-to-many relationship.

Notice the two ways to model a linking table. `order_items` carries its own surrogate key (`item_id`) plus two foreign keys, because a line item has data of its own (quantity, price) and other tables may want to reference it. `product_categories` carries nothing but the two foreign keys, so the pair itself is the primary key. Both are legitimate; pick by whether the link is a real entity or just a link.

That second pattern trips people up, so it is worth stating plainly: a column can be a foreign key and part of a primary key at the same time. The two are not mutually exclusive. One is about identity, the other about reference.

## A few things people get wrong

1. **Do not use business data as a primary key.** Emails and phone numbers change, and a primary key should not. Use a surrogate. Whether that surrogate is an auto-incrementing integer or a UUID is a real decision, which I went through in [choosing a primary key: UUID or auto-increment](/blog/choose-primary-key-uuid-or-auto-increment/).
2. **Foreign keys are not automatically indexed.** Yes, again. It is the single most common performance surprise in this whole topic.
3. **A foreign key does not have to share the parent's column name.** `orders.buyer_id` can reference `customers.customer_id` fine. The `REFERENCES` clause defines the link, not the name.
4. **Foreign keys do not prevent every orphan on their own.** They block invalid references, but only once you also pick the right `ON DELETE` and `ON UPDATE` behavior.

## Best practices, briefly

1. **Default to a surrogate primary key.** A system-generated `IDENTITY` or `SEQUENCE` value, or a UUID, over a natural business value. Keep it single-column and stable where you can.
2. **Index every foreign key** on a table that takes deletes or updates against its parent. One line, and the scan-the-child problem goes away.
3. **Name your constraints.** `fk_orders_customer` tells you what broke. An auto-generated name does not.
4. **Be explicit about `NOT NULL`.** Mandatory relationship, `NOT NULL`. Genuinely optional, nullable. Do not leave it to accident.
5. **Size the key type for growth.** `INT` tops out near 2.1 billion rows. Reach for `BIGINT` or a UUID before you get close, especially in sharded systems where a single auto-increment counter becomes a bottleneck.

<HintBlock type="info">

Getting keys and constraints right is a design-review problem, not only a one-time schema choice. [Bytebase](https://www.bytebase.com/)'s SQL review can flag a table created without a primary key, or a foreign key added without a supporting index, before the change ships. It is one of many [database design patterns](/blog/database-design-patterns/) worth enforcing the same way every time.

</HintBlock>

## Bottom line

A primary key is about identity. A foreign key is about reference. Keep the primary key stable, index the foreign keys, and most of your integrity problems never happen in the first place. After all, a key is only useful if the database can trust it.


Primary key vs foreign key: what each does and how they differ on uniqueness, NULLs, indexing, and relationships, with SQL examples and a comparison table.

The
Bytebase Blog

Explore the standard for database governance

Solutions & Platform

Resources

Change Management

Access & Security

AI & Agents

Comparisons

Company

Legal

The Bytebase Blog

Explore the standard for database governance

The
Bytebase Blog