How is this different from connecting dbt Labs MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the dbt Labs MCP API changes?

We track the dbt Labs MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different dbt Labs tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in dbt Labs?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the dbt Labs MCP server myself?

No. TrustGate connects to the dbt Labs MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to dbt Labs directly.

Connect dbt Labs MCP to your AI agents, securely.

Q: Is dbt Labs MCP secure?

The server itself exposes 27 tools, and some of them can write to your dbt Labs account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches dbt Labs.

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

Get started for free

Get a demo

Try dbt Labs MCP now

What your agents can ask once dbt Labs MCP is connected.

Select the tools your AI agents can call

27 tools from the dbt Labs MCP schema.

Showing 27 tools

list_metricsreadLists the metrics defined in the dbt Semantic Layer.
get_dimensionsreadGets the dimensions available for a given set of metrics.
get_entitiesreadGets the entities available for a given set of metrics.
get_dimension_valuesreadGets the distinct values for a dimension, optionally scoped to specific metrics.
query_metricsreadQueries metrics with grouping, filters and ordering through the Semantic Layer.
get_all_modelsreadRetrieves the name and description of all models in the project.
get_model_detailsreadGets the details of a model, including its columns, tests and compiled code.
get_model_parentsreadGets the upstream models and sources a model depends on.
get_model_childrenreadGets the downstream models that depend on a model.
get_all_sourcesreadGets all sources with their freshness status, optionally filtered by source name.
get_exposuresreadGets all exposures: the downstream dashboards, apps and analyses that consume the project.
get_all_macrosreadRetrieves the macros in the project, optionally filtered by package.
get_related_modelsreadFinds similar models using semantic search over the project.
execute_sqlhigh riskExecutes SQL on dbt Platform infrastructure with Semantic Layer support.
text_to_sqlreadGenerates SQL from natural language using the project's context.
listreadLists the resources in the dbt project by type, with selector support.
parsereadParses and validates the project files for syntax correctness.
compilereadCompiles the project without running anything against the warehouse.
showreadExecutes SQL against the database and returns the results.
runhigh riskExecutes models to materialise them in the database.
testwriteRuns tests to validate data and model integrity.
list_jobsreadLists the jobs defined on dbt Platform.
get_job_run_detailsreadGets the details and logs of a job run.
list_jobs_runsreadLists the runs of a job with their status and timing.
trigger_job_runhigh riskTriggers a job run on dbt Platform, materialising data in the warehouse.
get_mcp_server_versionreadReturns the current version of the dbt MCP server.
get_mcp_server_branchreadReturns the current git branch of the running dbt MCP server.

What dbt Labs MCP exposes

dbt Labs MCP groups its 27 tools into 6 categories, each with a suggested starting policy.

All 27 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Semantic Layer	Metrics, dimensions, entities and running semantic queries	Read	Requires a service token with Semantic Layer permissions
Discovery	Models, sources, macros, exposures, tests and lineage from the Discovery API	Read	Read-only metadata; safe to allow broadly
SQL	Executing SQL on dbt Platform infrastructure and generating it from natural language	Read / Write	SQL reaches the warehouse; scope the connection
dbt CLI	Running, building, testing, compiling and parsing the project locally	Read / Write	Self-hosted only; approve runs and builds against production targets
Admin API	Jobs, runs and projects on dbt Platform	Read / Write	Approve job triggers; they materialise data
Docs & Metadata	dbt documentation search and MCP server version information	Read	Allow documentation searches

Connect dbt Labs MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect dbt Labs
Find dbt Labs in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

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

dbt Labs MCP	27 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 27 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 dbt Labs 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.	dbt Labs MCP27 documented tools.
Coding assistants	Connection & credentialsper user	Discovery8 tools
Internal copilots	Tool access policiesdeny by default	dbt CLI6 tools
Workflow automations	Request & response inspectioninline	Semantic Layer5 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools8 tools