ClickHouse MCP Server connects AI assistants to ClickHouse, a database system for querying and analyzing data. It exposes tools for running read-only SQL queries and inspecting databases and tables, and the catalogue entries help agents connect to and use that server.
Borrowing it
Nothing to install: this file belongs to ClickHouse/mcp-clickhouse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ClickHouse/mcp-clickhouse/main/AGENTS.mdgit clone --depth 1 https://github.com/ClickHouse/mcp-clickhouseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/clickhouse/mcp-clickhouse/agents-md)<a href="https://agentmods.dev/instructions/clickhouse/mcp-clickhouse/agents-md"><img src="https://agentmods.dev/badge/instructions/clickhouse/mcp-clickhouse/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/clickhouse/mcp-clickhouse/agents-md"><img src="https://agentmods.dev/badge/instructions/clickhouse/mcp-clickhouse/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02213 | $0.02213 |
| Opus 5.5 | $0.00885 | $0.00885 |
| Sonnet 5.5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
mcp-clickhouse AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
AGENTS.md is the canonical instruction file for AI agents working in this repository. If another agent-facing file disagrees with this one, this file wins.
Before making substantial changes, read README.md, pyproject.toml, and the relevant source and tests. The README is part of the user-facing contract because it documents tools, response shapes, security behavior, and every supported environment variable.
Role
Act like an experienced maintainer of a public Python MCP server and database integration.
- Think about the MCP client experience, ClickHouse behavior, operational safety, and maintainability together.
- Be opinionated and practical. Do not over-engineer.
- Do not engage in sycophancy.
- If an assumption could materially affect security, compatibility, or the public tool contract, verify it or call it out explicitly.
Project Map
mcp_clickhouse/mcp_server.py: Startup assembly, FastMCP server construction, tool and prompt registration, and shutdown coordination.mcp_clickhouse/auth.py: Default dotenv loading, HTTP/SSE authentication, and FastMCP provider environment compatibility.mcp_clickhouse/transport.py: FastMCP HTTP/SSE app construction and trusted proxy integration.mcp_clickhouse/executors.py: Per-server query, metadata, cancellation, and health worker pools.mcp_clickhouse/chdb_backend.py: Per-server chDB state, lazy client initialization, query execution, and result processing.mcp_clickhouse/clients.py: Request configuration, connection diagnostics, readonly settings, and per-server ClickHouse client caches and leases.mcp_clickhouse/queries.py: Per-server ClickHouse query execution, active-query state, cancellation, and destructive-operation guards.mcp_clickhouse/metadata.py: Database and table discovery, metadata models, and per-server pagination state.mcp_clickhouse/health.py: Per-server health probes, result caching, and the public health route.mcp_clickhouse/serialization.py: JSON tool-result encoding and exact integer handling.mcp_clickhouse/http_security.py: Host and Origin validation and trusted proxy handling.mcp_clickhouse/mcp_env.py: environment-backed configuration and validation. Treat this as the source of truth for configuration semantics.mcp_clickhouse/main.py: runtime entry point and transport startup.mcp_clickhouse/mcp_middleware_hook.py: optional user-provided middleware loading.mcp_clickhouse/chdb_prompt.py: the public chDB prompt content.mcp_clickhouse/skills_advisor.py: server-level instructions advertised to MCP clients.tests/: unit, integration, FastMCP client, pagination, auth, middleware, and optional-dependency coverage.test-services/docker-compose.yaml: local ClickHouse service for integration tests..github/workflows/ci.yaml: authoritative CI commands and CI ClickHouse version.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +10 lines · +244 tokens per session 4c94f77c1b8d
- 1mo ago Changed 45d4f955d37b
- 2mo ago First seen · 148 lines · 1,969 tokens per session scan A 02016dbb2aa6
mcp-clickhouse AGENTS.md is an instructions file published in the GitHub repository ClickHouse/mcp-clickhouse (898 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,213 tokens to every session, about $0.0089 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.