MCP ClickHouse

55 tools. 27 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated:

27 can modify or destroy data
28 read-only
55 tools total

Community server · catalogue entry verified 12/06/2026

How to control MCP ClickHouse ↓

What MCP ClickHouse exposes to your agents

Read (28) Write / Execute (20) Destructive / Financial (7)
Critical Risk

The most dangerous MCP ClickHouse tools

27 of MCP ClickHouse's 55 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control MCP ClickHouse

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP ClickHouse, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "cloud_delete_api_key": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "cloud_create_api_key": {
    "limits": [
      {
        "counter": "cloud_create_api_key_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "cloud_get_activity": {
    "limits": [
      {
        "counter": "cloud_get_activity_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register MCP ClickHouse — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MCP CLICKHOUSE →

Free to start. No card required.

All 55 MCP ClickHouse tools

READ 28 tools
Read cloud_get_activity Get details of a specific activity. Read cloud_get_api_key Get details of a specific API key. Read cloud_get_available_regions Get information about available cloud regions. Read cloud_get_backup Get details of a specific backup. Read cloud_get_backup_configuration Get backup configuration for a service. Read cloud_get_clickpipe Get details of a specific ClickPipe. Read cloud_get_invitation Get details of a specific invitation. Read cloud_get_member Get details of a specific organization member. Read cloud_get_organization Get details of a specific organization. Read cloud_get_organization_metrics Get Prometheus metrics for all services in an organization. Read cloud_get_organization_private_endpoint_info Get private endpoint information for organization. Read cloud_get_private_endpoint_config Get private endpoint configuration for a service. Read cloud_get_query_endpoint_config Get query endpoint configuration for a service (experimental). Read cloud_get_reverse_private_endpoint Get details of a specific reverse private endpoint (beta). Read cloud_get_service Get details of a specific service. Read cloud_get_service_metrics Get Prometheus metrics for a service. Read cloud_get_usage_cost cloud_get_usage_cost Read cloud_list_activities List organization activities (audit log). Read cloud_list_api_keys List all API keys in an organization. Read cloud_list_backups List all backups for a service. Read cloud_list_clickpipes List all ClickPipes for a service. Read cloud_list_invitations List all pending invitations for an organization. Read cloud_list_members List all members in an organization. Read cloud_list_organizations List available ClickHouse Cloud organizations. Read cloud_list_reverse_private_endpoints List all reverse private endpoints for a service (beta). Read cloud_list_services List all services in an organization. Read list_databases List available ClickHouse databases. Read list_tables list_tables

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about MCP ClickHouse

Can an AI agent delete data through the MCP ClickHouse MCP server? +

Yes. The MCP ClickHouse server exposes 7 destructive tools including cloud_delete_api_key, cloud_delete_clickpipe, cloud_delete_invitation. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP ClickHouse? +

The MCP ClickHouse server has 17 write tools including cloud_create_api_key, cloud_create_clickpipe, cloud_create_invitation. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP ClickHouse.

How many tools does the MCP ClickHouse MCP server expose? +

55 tools across 4 categories: Destructive, Execute, Read, Write. 28 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on MCP ClickHouse? +

Register the MCP ClickHouse MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP ClickHouse tool call.

Deterministic rules across all 55 MCP ClickHouse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

55 MCP ClickHouse tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.