How is this different from connecting ClickHouse 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 ClickHouse MCP API changes?

We track the ClickHouse 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 ClickHouse 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 ClickHouse?

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 ClickHouse MCP server myself?

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

Connect ClickHouse MCP to your AI agents, securely.

Q: Is ClickHouse MCP secure?

The server itself exposes 3 tools, and some of them can write to your ClickHouse 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 ClickHouse.

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

Get started for free

Get a demo

Try ClickHouse MCP now

What your agents can ask once ClickHouse MCP is connected.

Select the tools your AI agents can call

3 tools from the ClickHouse MCP schema.

Showing 3 tools

list_databasesreadLists all ClickHouse databases available to the server, with optional SQL LIKE filtering.
list_tablesreadLists the tables in a database, with their schema and optional SQL LIKE filtering.
run_chdb_select_queryreadExecutes a SQL query using chDB's embedded ClickHouse engine, against files, URLs or databases.

What ClickHouse MCP exposes

ClickHouse MCP groups its 3 tools into 2 categories, each with a suggested starting policy.

All 3 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
ClickHouse	Database listing, table listing with filters and read-only SQL execution against the cluster	Read	Queries run read-only by default; keep write access off
chDB	Read-only SQL against files, URLs and databases through the embedded ClickHouse engine	Read	Enabled only when the chDB extra is installed

Connect ClickHouse 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 ClickHouse
Find ClickHouse 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 ClickHouse MCP or block it. You allow the exact tools each agent can call, one by one.

ClickHouse MCP	3 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 3 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 ClickHouse 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.	ClickHouse MCP3 documented tools.
Coding assistants	Connection & credentialsper user	ClickHouse2 tools
Internal copilots	Tool access policiesdeny by default	chDB1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs