How to Configure Make CockroachDB MCP Server

Published
Length
3 min read

Luis Felipe Dias

All posts

To set up a make cockroachdb mcp server workflow, link Make scenarios to your MCP host. The MCP server then uses a CockroachDB user role to run database queries. Many teams start by using one shared database admin key for all automated tasks. This broad role lets an automated step change or read any table by mistake. How the make cockroachdb mcp server setup works Make acts as a visual builder that links different apps and services together. A Make scenario starts when an event happens, such

Your coding agents run with your access.

Claude Code reaches prod with a developer's credentials, and approval prompts get clicked through. hoop.dev checks every query, masks sensitive data, and holds risky changes for a human.

To set up a make cockroachdb mcp server workflow, link Make scenarios to your MCP host. The MCP server then uses a CockroachDB user role to run database queries. Many teams start by using one shared database admin key for all automated tasks. This broad role lets an automated step change or read any table by mistake.

How the make cockroachdb mcp server setup works

Make acts as a visual builder that links different apps and services together. A Make scenario starts when an event happens, such as a new support ticket. Make then sends a request to an AI agent host or a custom service. That host talks to the CockroachDB MCP server using the Model Context Protocol. The MCP server turns tool requests from the AI model into standard SQL statements.

To run these statements, the MCP server must log in to the CockroachDB cluster. You create a specific SQL user inside your CockroachDB cluster for this job. You also set up network rules so the MCP server can reach the database. Next, you give that SQL user a role with read or write permissions. The MCP server stores the database login key and waits for Make to call it.

When the Make scenario runs, it passes data payload details to the AI model. The model picks an MCP tool to check or update records in CockroachDB. The MCP server runs the SQL query and sends the rows back to Make. Make then passes that answer to the next app in your workflow chain.

Where native database roles fall short in automation

Native CockroachDB roles do a good job of controlling who can log in. You can limit the MCP server user to specific schemas or specific tables. You can also make a read-only role so the workflow never deletes data. This setup stops unauthorized users from getting into your cluster from the outside.

Still, static database roles only check permissions at the table or schema level. Once the MCP server logs in, the database trusts every valid query it sends. If a table holds customer emails or card numbers, a read query pulls everything. Native roles do not rewrite matched fields in results before the AI model reads them. That means sensitive phone numbers or national IDs flow straight into Make and external models.

Kubernetes API Server Access + End-to-End Encryption: architecture patterns and best practices

Continue reading? Get the full guide.

Free. No spam. Unsubscribe anytime.

Shared service roles also make auditing very hard for your security team. Every query from Make looks like it came from the same MCP service user. You cannot see which workflow run or human user triggered a bad query. Also, if a workflow needs write permissions, one bad prompt can alter many rows. Static roles cannot pause a dangerous update statement and ask a human for approval.

Steps to harden your automated database workflows

Start by creating a separate CockroachDB SQL role for each distinct Make scenario. Never reuse a root or admin database user for an MCP server link. Grant each role permissions on only the exact tables that the workflow needs. If a Make scenario only checks order status, give that role select permissions only.

You should also limit which network addresses can reach your CockroachDB cluster nodes. Set up your cluster allowlist so only the MCP server host can connect. Turn on TLS so all traffic between the MCP server and database stays encrypted. Rotate the database keys stored in your MCP host on a regular schedule.

Check database and API queries on the wire

Identity tools, roles, and network rules decide who opens a session. Setup alone cannot check what each query does or mask sensitive values in a response once a session starts. When workflows touch Postgres, MySQL, SQL Server, MongoDB, ClickHouse, Kubernetes APIs, SSH, or internal HTTP APIs, hoop.dev runs beside those services as an open-source proxy, a sidecar for your Postgres or API. It inspects requests coming in and results going back on the wire.

Your login details and client tools stay as they are while hoop.dev guardrails refuse bad deletes or drops before they run. On responses, hoop.dev data masking rewrites matched sensitive values in memory. Furthermore, hoop.dev holds SOC 2 Type II, is MIT licensed, and writes every query and decision to an audit trail that generates evidence for HIPAA, GDPR, and PCI DSS. See the source on GitHub.

Frequently asked questions

Can Make talk directly to a CockroachDB MCP server?

Make triggers an AI host or service via HTTP requests or custom webhooks. That host runs the MCP client, which talks to the CockroachDB MCP server.

What database permissions should I give the MCP server?

Give the MCP server a custom SQL role with the least privilege needed. Stick to read-only permissions on specific tables unless the workflow must write data.

How do I keep card numbers out of AI prompts in Make?

Standard database roles return full rows if the user has read access on tables. To hide card numbers or emails, use data masking that rewrites matched fields in results.

The query runs. The emails stay hidden.