Clickhouse MCP | Bearer Token Clickhouse connector for AI agents

CALL ANY TOOL

Run SQL queries, list databases and tables, inspect schemas, and retrieve query execution logs.

ch_query_run

Run query

Execute a ClickHouse SQL query and return results.

Parameters

Name

Type

Required

Description

query

string

Required

ClickHouse SQL query

database

string

Optional

Target database name

max_rows

integer

Optional

Max rows to return

ch_databases_list

List databases

ch_tables_list

List tables

ch_table_schema

Get table schema

ch_query_log

Get query log

Build your Agent

Drop the toolkit in, point it at the user, and your analytics agent can use Clickhouse from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["clickhouse"], toolNames: ["ch_query_run", "ch_databases_list", "ch_tables_list"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["clickhouse"], toolNames: ["ch_query_run", "ch_databases_list", "ch_tables_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["clickhouse"], toolNames: ["ch_query_run", "ch_databases_list", "ch_tables_list"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/clickhouse",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Clickhouse.

Schema & discovery

List all databases.

Show tables in [database].

Copy the prompt

Copied

Get schema for [database.table].

Copy the prompt

Copied

How many rows are in [table]?

Query & analysis

Copy the prompt

Copied

Run: SELECT event_type, count() FROM events GROUP BY event_type.

Copy the prompt

Copied

Daily active users last 30 days.

Copy the prompt

Copied

Top 10 customers by API call volume.

Copy the prompt

Copied

P99 latency by endpoint last week.

Monitoring & ops

Copy the prompt

Copied

Recent slow queries over 5 seconds.

Copy the prompt

Copied

Query log for user [username] today.

Copy the prompt

Copied

Which tables have the most reads?

Copy the prompt

Copied

Storage size by database.

SEE HOW AUTH WORKS

Users authorize Clickhouse once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Clickhouse

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Clickhouse

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Clickhouse

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Clickhouse

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other analytics agents and MCP connectors. Working code, live demos, fork what fits.

GTM

HubSpot to Slack updates agent

Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.

HubSpot

Slack

View agent

ENGINEERING

Engineering standup agent

Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Clickhouse today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Clickhouse as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Clickhouse bearer token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Clickhouse?

Yes. Pass a tool name filter to listScopedTools so the analytics agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Clickhouse.

What happens when a user revokes Clickhouse access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Does the agent inherit ClickHouse user roles and row-level access policies?

Yes. Queries run under the authorizing user's ClickHouse credentials. Role-based access, row-level policies, and database-level grants all apply. The agent cannot read what the user cannot.

Clickhouse

Tools your analytics agent reaches for on Clickhouse, scoped per user.