mcpbeat Sign in

Setup Agent Skill

Guides users through setting up the ClickHouse MCP server connection bundled with this plugin. Use when the user first installs the plugin or has trouble connecting to ClickHouse.

906 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
0
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/ClickHouse/clickhouse-claude-code-plugin --skill setup

The instruction itself

11 sections, as written by the author

ClickHouse Plugin Setup

This plugin includes the ClickHouse Cloud Remote MCP server at https://mcp.clickhouse.cloud/mcp. It provides secure, read-only access to your ClickHouse Cloud clusters.

Setup Steps

  • Verify the MCP server is connected: Check that the ClickHouse MCP server appears in your available tools. If it does, you're ready to go.
  • Authenticate via OAuth: The MCP server uses OAuth with your ClickHouse Cloud credentials. Follow the prompts when first connecting to authorize access.
  • Test the connection: Try listing databases or running a simple SELECT query to confirm everything works.

Troubleshooting

  • Server not appearing: Run /plugin to confirm the plugin is installed and enabled, then restart the Grok session to reload plugin MCP servers.
  • Authentication errors: Re-authenticate by following the OAuth flow when prompted.
  • Connection timeouts: Verify your network can reach https://mcp.clickhouse.cloud. The MCP server is a remote HTTP endpoint and requires internet access.

MCP Tool Call Timeouts

Agent hosts cap how long a single MCP tool call may run, and that cap is typically far shorter than ClickHouse's own query timeout. The run_select_query tool accepts a timeoutSeconds parameter (default 300s, max 3600s), but the host kills the connection at its own limit regardless of this setting — raising timeoutSeconds will not make a slow query succeed.

Implications:

  • Keep queries simple and fast — complex analytical queries will be cut off before they return
  • Use LIMIT clauses to bound result sets
  • Prefer querying materialized views or pre-aggregated tables over raw scans of large tables
  • If a query times out, break it into smaller, faster queries rather than increasing timeoutSeconds

What the MCP Server Provides

Once connected, the ClickHouse MCP server provides these tools:

Organization & Service Management

  • get_organizations — list all accessible ClickHouse Cloud organizations
  • get_organization_details — details of a single organization
  • get_services_list — list all services in an organization
  • get_service_details — details of a single service

Database Exploration

  • list_databases — list all databases in a service
  • list_tables — list tables in a database (supports like/notLike filtering)
  • run_select_query — execute read-only SELECT queries (⚠️ subject to the host's MCP tool call timeout)

ClickPipes

  • list_clickpipes — list all ClickPipes for a service
  • get_clickpipe — details of a specific ClickPipe

Backups

  • list_service_backups — list all backups for a service
  • get_service_backup_details — details of a specific backup
  • get_service_backup_configuration — backup schedule and retention settings

Billing

  • get_organization_cost — billing and usage cost data (max 31-day window)

All tools are read-only. See the ClickHouse MCP docs for details.

Best Practices Skill

This plugin also includes the clickhouse-best-practices skill with 31 rules covering schema design, query optimization, and insert strategy. That skill activates automatically when you work with ClickHouse -- no setup needed.

Other skills for the same job

different authors, same section of the catalogue
Clawdirect Dev
by ComeOnOliver
×1

Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite, and ATXP.

13k tokens
Mem Search
by thedotmack

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

1k tokens
Deepagents Thread Inspector
by langchain-ai
vendor

Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse ~/.deepagents/.state/sessions.db and a thread UUID or prefix.

7k tokens scripts
Hive Terminal Tools Pty Sessions
by aden-hive

Use when you need state across calls — building env vars, navigating with cd, driving REPLs (python -i, mysql, psql, node), or responding to interactive prompts (sudo password, ssh host-key confirmation, mysql connection). Teaches the prompt-sentinel exec pattern (default mode), raw I/O for REPLs (raw_send=True then read_only=True), the one-in-flight-per-session rule, and the close-or-leak-against-the-cap discipline. Bash on macOS — never zsh; explicit shell=/bin/zsh is rejected. Read before calling terminal_pty_open.

1k tokens
Deepchat Data Import
by ThinkInAIXYZ

Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, `agent.db`, `chat.db`, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.

6k tokens
Agent Team
by anbeime

统一管理多智能体角色的团队协作框架,支持智能体动态组合、灵活协作和扩展新角色。智能体本质上是"角色定义",可以根据任务需求灵活组建团队,实现从会议决策到系统构建的完整能力。智能体角色明确分工:有干活的、有指挥的、有挑毛病的,能实时看到沟通过程,共享数据库记忆,确保上下文一致。

25k tokens zh
Recall
by parcadei

Query the memory system for relevant learnings from past sessions

313 tokens
Transcript Fixer
by daymade

>- Corrects speech-to-text transcription errors using dictionary rules and Claude's built-in AI (no external API key required — Native AI Correction is the DEFAULT). Stage 3 API is a backup for automation without Claude Code. Builds personalized correction databases that learn from each fix, auto-loads person-name ASR variants from your people roster, and reads per-domain context files that prime the AI pass for context-dependent homophones. Triggers when working with ASR/STT output containing recognition errors, homophones, garbled technical terms, person-name errors, or Chinese/English mixed content. Also triggers on requests to clean up meeting notes, lecture transcripts, interview recordings, or any text produced by speech recognition. Use this skill even when the user just says "fix this transcript", "clean up these meeting notes", or mentions garbled names without invoking ASR specifically.

297k tokens scripts

How to use it

Copy the folder

Take clickhouse/setup from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.