Skip to content

Integration · Automate and collaborate

PlanetScale and Meteor AI agents

Connect PlanetScale to an internal Met: check databases, branches and schemas, find slow or failing queries and see CPU and memory.

How does PlanetScale connect to Meteor?

With the PlanetScale ready connector, your Met uses PlanetScale's official MCP server with the account the admin authorizes. When authorizing you choose no access, read-only or full access to each database. The Met lists organizations, databases and branches, brings the schema, runs read queries, shows performance insights, failing queries and schema recommendations, and checks CPU, memory, disk and connections. Running write SQL starts turned off until the admin turns it on, and it also needs full access; PlanetScale blocks UPDATE or DELETE without WHERE and TRUNCATE. It also checks invoices and PlanetScale's documentation.

What it automates

What a Meteor Met does with PlanetScale

Find out why the database is slow

When someone on the team reports on WhatsApp that the app is slow, the Met checks the main branch's CPU, memory and connections, brings the query insights and schema recommendations, and sums up what it found.

Find the failing queries

The Met lists query errors grouped by pattern and opens the executions of the most frequent one, with the SQL and the tables it touches.

Answer a fact from the database

If the access allows queries, the Met checks the branch schema and runs a read query, which goes to a replica by default, to answer with the fact.

Explain the month's invoice

The Met lists the organization's invoices and opens the latest one's line items, with the cost per branch, so you know which database weighs the most.

23 tools

Everything your Met can ask PlanetScale for

Each one is a real action in the connector. You can switch off the ones you would rather it never used.

Tool What it does
planetscale_list_organizations Lists the PlanetScale organizations you have access to.
planetscale_get_organization Returns the details of an organization.
planetscale_list_databases Lists the databases in an organization.
planetscale_get_database Returns the details of a database.
planetscale_list_branches Lists the branches of a database.
planetscale_get_branch Returns the details of a database branch.
planetscale_get_branch_schema Returns the schema of a database branch.
planetscale_execute_read_query Runs a read-only query (SELECT, SHOW, DESCRIBE, EXPLAIN), on a replica by default if one exists.
planetscale_execute_write_query Runs a write query (INSERT, UPDATE, DELETE or DDL) on a PlanetScale database. Starts turned off.
planetscale_get_insights Returns query performance insights for a branch.
planetscale_list_schema_recommendations Lists schema recommendations, such as adding indexes, removing redundant indexes or preventing primary key exhaustion.
planetscale_list_query_error_patterns Lists the failing queries on a branch, grouped by error, with the message, how many times it happened and the last time.
planetscale_list_query_error_executions Lists the failed executions behind an error pattern, with the normalized SQL, tables, user and duration.
planetscale_get_postgres_logs Returns a Postgres branch's server logs, newest first, with filters by level and time. Postgres only.
planetscale_list_query_tags Lists the query tags seen on a branch, with their values and how many queries carry each one.
planetscale_get_query_tag Returns a query tag and its values.
planetscale_list_query_tag_summaries Groups query statistics by tag and attributes time, latency, rows read and errors to an app, route, job or user.
planetscale_get_branch_metrics Returns a branch's CPU, memory, disk, replication lag and connections, with a summary of the last hour.
planetscale_list_regions_for_organization Lists the regions available to an organization.
planetscale_list_cluster_size_skus Lists the available cluster sizes.
planetscale_list_invoices Lists an organization's invoices.
planetscale_get_invoice_line_items Returns an invoice's line items, with prorated costs per branch.
planetscale_search_documentation Searches the PlanetScale documentation.

The limits

What the PlanetScale integration does NOT do

We would rather say it here than have you find out during rollout.

Before you start

What you need to connect PlanetScale

  1. 1

    A PlanetScale account with access to your databases

    The account your team manages its databases with. Its role limits the permissions it can grant when authorizing.

  2. 2

    Connect it in Met

    In Met, open Connections → PlanetScale → Connect. A PlanetScale window opens so you sign in and authorize Met; there you choose the access to each database.

Frequently asked questions

Questions about PlanetScale and Meteor

Yes. In the authorization you choose read-only access to the databases. The organization admin can also set MCP query access in Settings to read-only or no queries for everyone.

Only if the admin turns on write SQL in Connections, which starts turned off, and you authorized full access. Even then, PlanetScale blocks UPDATE or DELETE without WHERE and TRUNCATE. If you do not want it to write, authorize read-only.

Read queries go to a replica by default when the branch has replicas. They all carry the source=planetscale-mcp comment so you can spot them in Insights.

You do, with your own PlanetScale plan. Meteor does not resell PlanetScale: the connector uses your company's account.

Step by step

Automations that use PlanetScale

Complete tasks, with the steps and the tools that run at each one.

Automate and collaborate

Other integrations in the same family

Want to see a Met running PlanetScale?

We will show you with your own account connected, not with a canned demo.