Connect AI agents to the Planet Scale MCP server

Vendor MCP

The Planet Scale MCP connector routes your AI agent's tool calls to Planet Scale's own MCP server through Scalekit. Each user signs in to Planet Scale once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 16 tools.

Tools: 16
What they doRead · write · destructive: 15 · 0 · 115 read0 write1 destructive
Users sign in with: OAuth
OAuth app: Scalekit's or your own

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Planet Scale MCP connection
In AgentKit > Connections, create a Planet Scale MCP connection. The name you give it is the connection_name your code passes. See Configure connections.
Scalekit credentials are available for Planet Scale MCP server, so you don't need to register an OAuth app.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'planetscalemcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Planet Scale MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'planetscalemcp_planetscale_list_organizations',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "planetscalemcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Planet Scale MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="planetscalemcp_planetscale_list_organizations",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

planetscalemcp_planetscale_execute_read_queryExecute a read-only SQL query (SELECT, SHOW, DESCRIBE, EXPLAIN) against a PlanetScale database branch.Read-only
Planetscale Execute Read Query
Execute a read-only SQL query (SELECT, SHOW, DESCRIBE, EXPLAIN) against a PlanetScale database branch.
Inputs
branchstringrequired
Branch name (e.g., 'main')
databasestringrequired
Database name
organizationstringrequired
PlanetScale organization name
querystringrequired
SQL SELECT query to execute
postgres_database_namestring
Postgres only: target database name to connect to. Use when the user has created additional databases in the same PlanetScale Postgres cluster (e.g. via CREATE DATABASE). Omit to use the default database for the branch.
use_replicaboolean
Route read queries to a read replica when the branch has replicas. Defaults to true. Set false to force the primary.
planetscalemcp_planetscale_get_branchGet details about a specific database branch.Read-only
Planetscale Get Branch
Get details about a specific database branch.
Inputs
pathParametersobjectrequired
No description.
planetscalemcp_planetscale_get_branch_schemaGet the schema (tables and columns) for a specific database branch.Read-only
Planetscale Get Branch Schema
Get the schema (tables and columns) for a specific database branch.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_get_databaseGet details about a specific PlanetScale database.Read-only
Planetscale Get Database
Get details about a specific PlanetScale database.
Inputs
pathParametersobjectrequired
No description.
planetscalemcp_planetscale_get_insightsGet query performance insights for a PlanetScale database branch, including top queries aggregated over a time period.Read-only
Planetscale Get Insights
Get query performance insights for a PlanetScale database branch, including top queries aggregated over a time period.
Inputs
branchstringrequired
Branch name (e.g., 'main')
databasestringrequired
Database name
organizationstringrequired
PlanetScale organization name
fieldsarray
Request specific metric fields from the API (e.g. ['query', 'count', 'rowsRead', 'rowsAffected', 'rowsReadPerReturned', 'egressBytes', 'indexes', 'maxShardQueries']). Ignored when fingerprint is provided.
fingerprintstring
Query fingerprint hash to drill down into a specific query pattern. Use the `fingerprint` value from an initial insights call. Always include `keyspace` (also from the initial results) to get summary data.
fromstring
Start of time range (ISO 8601 format, e.g. '2026-03-09T00:00:00.000Z'). Defaults to 24 hours ago. Supported in both discovery and fingerprint modes.
keyspacestring
Keyspace for fingerprint drill-down. Required to get summary data. Use the `keyspace` value returned in insights results (e.g. 'my_keyspace' for MySQL/Vitess or 'postgres.public' for Postgres databases).
limitnumber
Number of results per metric (default: 5, max: 20)
periodstring
Shorthand for a recent time window ending at now. Valid values: '15m', '1h', '3h', '6h', '12h', '24h'. Cannot be combined with from/to — use one or the other. Only supported in discovery mode (ignored in fingerprint mode — use from/to instead).
querystring
Filter insights by search query. Supports plain text matching and structured filters: exact match with quotes ("select count"), statement_type:select|delete|update|insert, table:table_name, keyspace:keyspace_name, table_keyspace:keyspace_name, index:index_name or index:table.index_name, indexed:true|false, multishard:true|false, query_count:>N or query_count:<N, p99:>N or p50:<N (ms), max_latency:>N (ms). Ignored when fingerprint is provided.
sort_bystring
Sort order: 'all' (default) aggregates curated API calls for a comprehensive view, or specify a single metric: 'count', 'percentTime', 'totalTime', 'cpuTime', 'p50Latency', 'p99Latency', 'rowsRead', 'rowsReadPerQuery', 'rowsReadPerReturned', 'rowsAffected', 'egressBytes', 'egressBytesPerQuery', 'maxEgressBytes', 'ingressBytes', 'ingressBytesPerQuery', 'maxIngressBytes'. 'cpuTime' is Postgres-only; 'maxEgressBytes' and ingress* are MySQL/Vitess-only. Ignored when fingerprint is provided.one of allcountpercentTimetotalTimecpuTimep50Latencyp99LatencyrowsReadrowsReadPerQueryrowsReadPerReturnedrowsAffectedegressBytesegressBytesPerQuerymaxEgressBytesingressBytesingressBytesPerQuerymaxIngressBytes
tablet_typestring
Filter by tablet type: 'primary' or 'replica'one of primaryreplica
tostring
End of time range (ISO 8601 format). Defaults to now. Supported in both discovery and fingerprint modes.
planetscalemcp_planetscale_get_invoice_line_itemsGet all line items for a specific invoice, broken down by database branch costs.Read-only
Planetscale Get Invoice Line Items
Get all line items for a specific invoice, broken down by database branch costs.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_get_organizationGet details about a specific PlanetScale organization.Read-only
Planetscale Get Organization
Get details about a specific PlanetScale organization.
Inputs
pathParametersobjectrequired
No description.
planetscalemcp_planetscale_list_branchesList all branches within a PlanetScale database.Read-only
Planetscale List Branches
List all branches within a PlanetScale database.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_list_cluster_sizesList available PlanetScale cluster sizes (SKUs) for an organization.Read-only
Planetscale List Cluster Sizes
List available PlanetScale cluster sizes (SKUs) for an organization.
Inputs
organizationstringrequired
PlanetScale organization name
enginestring
Database engine to list SKUs for (default: mysql)one of mysqlpostgresql
typestring
Filter to only autoscaling (PS-*, network-backed) or metal (M-*, local storage) sizesone of autoscalingmetal
planetscalemcp_planetscale_list_databasesList all databases within a PlanetScale organization.Read-only
Planetscale List Databases
List all databases within a PlanetScale organization.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_list_invoicesList all invoices for a PlanetScale organization.Read-only
Planetscale List Invoices
List all invoices for a PlanetScale organization.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_list_organizationsList all PlanetScale organizations you have access to.Read-only
Planetscale List Organizations
List all PlanetScale organizations you have access to.
Inputs
queryParametersobject
No description.
planetscalemcp_planetscale_list_regions_for_organizationList the regions available for a PlanetScale organization.Read-only
Planetscale List Regions For Organization
List the regions available for a PlanetScale organization.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_list_schema_recommendationsList all schema recommendations for a PlanetScale database based on production query patterns.Read-only
Planetscale List Schema Recommendations
List all schema recommendations for a PlanetScale database based on production query patterns.
Inputs
pathParametersobjectrequired
No description.
queryParametersobject
No description.
planetscalemcp_planetscale_search_documentationSearch the PlanetScale knowledge base for documentation, API references, code examples, and guides.Read-only
Planetscale Search Documentation
Search the PlanetScale knowledge base for documentation, API references, code examples, and guides.
Inputs
querystringrequired
Search query for PlanetScale docs
api_reference_onlyboolean
Only return API reference docs
code_onlyboolean
Only return code snippets
languagestring
Optional language filter (e.g., 'en', 'es')
versionstring
Optional version filter (e.g., 'v0.7')
planetscalemcp_planetscale_execute_write_queryExecute a write SQL query (INSERT, UPDATE, DELETE, or DDL) against a PlanetScale database branch.Destructive
Planetscale Execute Write Query
Execute a write SQL query (INSERT, UPDATE, DELETE, or DDL) against a PlanetScale database branch.
Inputs
branchstringrequired
Branch name (e.g., 'main')
databasestringrequired
Database name
organizationstringrequired
PlanetScale organization name
querystringrequired
SQL INSERT/UPDATE/DELETE/DDL query to execute
confirm_destructiveboolean
HUMAN CONFIRMATION REQUIRED: Only set to true after explicitly asking the user and receiving their approval. Show them the exact DELETE or DDL query first.
postgres_database_namestring
Postgres only: target database name to connect to. Use when the user has created additional databases in the same PlanetScale Postgres cluster (e.g. via CREATE DATABASE). Omit to use the default database for the branch.

Setup

Install the SDK

Set your credentials

Create the Planet Scale MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Planetscale Execute Read Query

Inputs

Planetscale Get Branch

Inputs

Planetscale Get Branch Schema

Inputs

Planetscale Get Database

Inputs

Planetscale Get Insights

Inputs

Planetscale Get Invoice Line Items

Inputs

Planetscale Get Organization

Inputs

Planetscale List Branches

Inputs

Planetscale List Cluster Sizes

Inputs

Planetscale List Databases

Inputs

Planetscale List Invoices

Inputs

Planetscale List Organizations

Inputs

Planetscale List Regions For Organization

Inputs

Planetscale List Schema Recommendations

Inputs

Planetscale Search Documentation

Inputs

Planetscale Execute Write Query

Inputs

Related: other Databases connectors