Data · MCP Server
Securing the dbt MCP server
The dbt MCP server gives an agent model metadata, lineage, and transformation runs. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.
What the server hands your agent
Project and model metadata, lineage graphs, compiled SQL, and command execution such as run, build, and test.
Why it is worth governing
- A run rebuilds tables that downstream dashboards and reverse-ETL syncs depend on, so a bad model change propagates fast.
- Compiled SQL exposes the full shape of your data model, including columns an agent has no reason to see.
- Project files hold warehouse connection detail.
Tag what the tools actually do
Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for dbt:
| Tool pattern | Tags | Why |
|---|---|---|
| mcp__dbt__*run* | critical_action | a run rewrites warehouse tables |
| mcp__dbt__*build* | critical_action | build mutates downstream models |
Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.
The policy
Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.
settings:
tool_tags:
enabled: true
mode: observe # switch to enforce once the log looks right
tags:
"mcp__dbt__*run*": [critical_action]
"mcp__dbt__*build*": [critical_action]
rules:
- "untrusted_content then critical_action -> block"Putting dbt behind the gateway
You do not change the dbt server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:
prismor mcp-gateway install # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall # restores the original, backup keptYour agent sees the same dbt tools, namespaced as mcp__dbt__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.
Frequently asked questions
Is the dbt MCP server safe to give an AI agent?
It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine dbt access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.
Does Prismor replace the dbt MCP server?
No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.
Will this block work my team actually needs to do?
Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.
What about tool results, not just tool calls?
Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.
One gateway for every MCP server
dbt is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.
Other data servers
PostgreSQL
MongoDBdbt is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The dbt MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.