ClickHouse (Vector Search)

ClickHouse (Vector Search) MCP Connector for Claude

A+

Manage vector embeddings and SQL via ClickHouse — list databases, execute SQL, and perform high-speed vector searches directly from any AI agent.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your ClickHouse cluster to any AI agent and take full control of your analytical and vector data through natural conversation.

What you can do

  • Schema Management — List databases and tables, and inspect deep column schemas including specialized Array(Float32) vector types
  • SQL Execution — Push arbitrary DML, DDL, or SELECT queries to your cluster to manage data and generate real-time reports
  • Vector Search — Identify mathematical distance traces using cosineDistance or L2Distance metrics for high-dimensional semantic search
  • Cluster Monitoring — Extract internal structural states, row counts, and compression ratios to audit cluster health
  • Capability Auditing — Check instance versions and binary limits to identify exact capability branches like HNSW support

How it works

  1. Subscribe to this server
  2. Enter your ClickHouse URL (Cloud or self-hosted), Username, and Password
  3. Start querying your analytical data from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Data Analysts — generate complex analytical reports and execute SQL queries using natural language
  • AI Developers — test and debug vector similarity searches and semantic matching without writing boilerplate code
  • Database Administrators — monitor table statistics, compression ratios, and cluster versions across environments
  • Product Teams — quickly verify analytical data and vector distributions during the prototyping phase
olapvector-embeddingssql-executionhigh-performance-datareal-time-analytics

7 tools expose this connector's capabilities to your AI agent.

list_databases

Identify bounded logical arrays managing top-level ClickHouse schemas

list_tables

Retrieve the exact structural matching verifying table limits inside a database

describe_table

Perform structural extraction of properties driving active column schemas

execute_sql

Provision a highly-available SQL execution pushing arbitrary arbitrary DML/DDL or SELECTs

vector_search

Identify explicit mathematical distance traces routing Vector Embeddings

get_table_stats

Extracts explicitly attached internal structural states pulling cluster health

get_version

g. HNSW support). Identify precise active cluster limits spanning the execution runtime

See how to talk to your AI agent using ClickHouse (Vector Search).

List all databases in my ClickHouse cluster

I found 4 databases: 'default', 'analytics_prod', 'vector_store', and 'system'. Which one would you like to explore?

Find the top 5 most similar records in table 'embeddings' using this vector: [0.1, 0.5, -0.2]

Vector search complete! I found 5 matches in 'analytics_prod.embeddings'. The top match has a cosineDistance of 0.045. Would you like to see the associated metadata for these records?

Get table stats for 'analytics_prod.sales_data'

Stats for 'sales_data': 1.2M rows, 450MB total size, 4.2x compression ratio. The table is currently healthy and responsive.

Yes. Provide the database, table, and the vector embedding array in JSON format. The agent uses ClickHouse's native distance functions (cosine or L2) to return the closest matches, leveraging ClickHouse's industry-leading OLAP performance.

Related Connectors