NeuralTrust has been recognized by Gartner → Read more

Connect PlanetScale MCP to your AI agents, securely.

One secured endpoint for every PlanetScale call your AI agents make, scoped per user, inspected, and logged.

Select the tools your AI agents can call

26 tools from the PlanetScale MCP schema.

Showing 26 tools

  • planetscale_list_organizationsreadLists all PlanetScale organizations you have access to.
  • planetscale_list_databasesreadLists all databases within an organization.
  • planetscale_list_branchesreadLists all branches within a database.
  • planetscale_get_organizationreadGets details about a specific organization.
  • planetscale_get_databasereadGets details about a specific database.
  • planetscale_get_branchreadGets details about a database branch.
  • planetscale_get_branch_schemareadGets the schema for a database branch.
  • planetscale_list_schema_recommendationsreadLists schema recommendations for a database: adding indexes, removing redundant ones and preventing primary key exhaustion.
  • planetscale_execute_read_queryreadExecutes a read-only SQL query (SELECT, SHOW, DESCRIBE, EXPLAIN). Routes to a replica by default; use_replica false targets the primary. On Postgres it runs under a role that does not bypass row-level security and returns RLS warnings when policies may be filtering results.
  • planetscale_execute_write_queryhigh riskExecutes a write SQL query (INSERT, UPDATE, DELETE or DDL). UPDATE and DELETE without a WHERE clause are blocked, TRUNCATE is blocked, and DDL prompts for human confirmation.
  • planetscale_get_insightsreadGets query performance insights for a database branch.
  • planetscale_list_query_error_patternsreadLists failing queries for a branch, aggregated by error fingerprint, with the error message, occurrence count, last run and durations.
  • planetscale_list_query_error_executionsreadLists the individual failed executions behind an error fingerprint, including the normalized SQL, tables, keyspace, user, row counts, duration and query tags.
  • planetscale_get_postgres_logsreadFetches server logs for a Postgres branch, newest first, filterable by level, time range, server role and pod, or by a raw LogsQL query. Postgres only.
  • planetscale_get_branch_metricsreadInfrastructure metrics for a branch: CPU, memory, disk, replication lag and connections. The default summary covers the last hour; memory utilization includes page cache, so RSS and cache are reported separately.
  • planetscale_list_query_tagsreadLists the query tags seen on a branch's queries, with their values and query counts.
  • planetscale_get_query_tagreadGets a single query tag and its values, using a tag ID from the tag listing.
  • planetscale_list_query_tag_summariesreadGroups query statistics by tag values, attributing total time, latency, rows read and errors to an application, route, job or user.
  • planetscale_list_regions_for_organizationreadLists all available regions for an organization.
  • planetscale_list_cluster_size_skusreadLists all available cluster size SKUs.
  • planetscale_list_invoicesreadLists all invoices for an organization.
  • planetscale_get_invoice_line_itemsreadGets all line items for an invoice, with prorated costs broken down by database branch.
  • planetscale_get_organization_billing_payment_methodreadShows the organization's current payment method.
  • planetscale_update_payment_methodhigh riskStarts Stripe Checkout to add or replace the organization's card, returning a checkout_url and setup_id. Requires Payment method full access.
  • planetscale_get_payment_method_setupreadChecks a Checkout setup by setup_id. Does not poll; a second update should not be started while one is pending.
  • planetscale_search_documentationreadSearches the PlanetScale documentation.

What PlanetScale MCP exposes

PlanetScale MCP groups its 26 tools into 8 categories, each with a suggested starting policy.

All 26 tools as JSON, ready to paste.

CategoryCoversAccessSuggested policy
ResourcesOrganizations, databases and branches, by listing and by detailReadPin the organization, database and branch in your AGENTS.md so the agent skips the discovery scan
Insights & DiagnosticsQuery performance insights, failing query patterns and their executions, Postgres server logs and branch infrastructure metricsReadLogs and error executions can contain query text; treat as sensitive
BillingInvoices, invoice line items prorated per branch, and the organization payment methodRead / WritePayment method access is a separate OAuth scope; full access is needed to update the card
Query TagsQuery tags seen on a branch, their values, and statistics grouped by tag to attribute time to an application, route, job or userReadRead-only attribution reporting
SchemaBranch schema and schema recommendations for indexes and primary key exhaustionReadSafe to allow; recommendations are advisory only
QueriesRead and write SQL execution against a branch, over HTTP with ephemeral credentialsRead / WriteThe insights-only server URL excludes both query tools entirely; use it when no execution is needed
Platform ReferenceAvailable regions and cluster size SKUs for an organizationReadReference lookups; safe to allow broadly
DocumentationSearch across the PlanetScale documentationReadAllow documentation searches

Connect PlanetScale MCP to your AI agent

Four steps, under ten minutes.

  1. 01

    Sign in to NeuralTrust

    Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.

    Sign in to NeuralTrust
  2. 02

    Choose your agent

    When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.

    Choose your agent
  3. 03

    Connect PlanetScale

    Find PlanetScale in the tool list and connect it.

    Connect PlanetScale
  4. 04

    Connect your agent

    Follow the steps on screen to add the config to your agent, then send the test prompt.

    Connect your agent

Permissions down to the single tool

You do not allow PlanetScale MCP or block it. You allow the exact tools each agent can call, one by one.

PlanetScale MCP26 TOOLS AVAILABLE
Code review agent4 tools, read only
Issue triage bot9 tools
Platform team assistantall 26 tools
  • Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
  • Default denyA tool you have not enabled is never exposed to the agent.
  • Approval on writesTools that change or delete things can require a human to confirm.

Is PlanetScale MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.NeuralTrustApply controls based on your configuration.PlanetScale MCP26 documented tools.
Coding assistantsConnection & credentialsper userResources6 tools
Internal copilotsTool access policiesdeny by defaultInsights & Diagnostics5 tools
Workflow automationsRequest & response inspectioninlineBilling5 tools
Compatible MCP clientsActivity monitoringalerts and logsAll other tools10 tools
FAQ

Common questions about running PlanetScale MCP through TrustGate.

Connect PlanetScale MCP instantly

Pick the tools, point your agent at TrustGate, and PlanetScale MCP is live: scoped, inspected, logged.