What is mcp-trino CLAUDE.md?

Project instructions for mcp-trino, an open-source connector that lets AI assistants query Trino data warehouses through the Model Context Protocol.

They guide contributions, explanations, reviews, and other work on the connector while requiring facts to be checked against the project.

They reduce unverified claims and set expectations for secure, reusable work with data systems.

How txn2/mcp-trino configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to txn2/mcp-trino. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/txn2/mcp-trino/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/txn2/mcp-trino

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/txn2/mcp-trino/claude-md/github.svg)](https://agentmods.dev/instructions/txn2/mcp-trino/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/txn2/mcp-trino/claude-md"><img src="https://agentmods.dev/badge/instructions/txn2/mcp-trino/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/txn2/mcp-trino/claude-md"><img src="https://agentmods.dev/badge/instructions/txn2/mcp-trino/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,253 This file is loaded in full into every session.

When invoked 3,253 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03253	$0.03253
Opus 5.5	$0.01301	$0.01301
Sonnet 5.5	$0.00651	$0.00651
Haiku 4.5	$0.00325	$0.00325

Measured 26d ago against content hash 4994eff604e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-trino CLAUDE.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 26d 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.

CLAUDE.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with this project.

Project Overview

mcp-trino is a generic, open-source MCP (Model Context Protocol) server for Trino. It enables AI assistants to query and explore data warehouses via the MCP protocol.

Key Design Goals:

Composable: Can be used standalone OR imported as a library
Generic: No domain-specific logic; suitable for any Trino deployment
Secure: Configurable limits and timeouts to prevent abuse

CRITICAL - Factual Integrity (No Confabulation)

AI-generated prose (PR descriptions, commit messages, reviews, explanations) is held to the same verification standard as code. Unverified claims are as unacceptable as untested code.

Never assert facts you haven't verified. Before stating that a file contains X, a config is missing Y, or a system behaves in way Z — READ the file, CHECK the config, VERIFY the behavior. If you haven't looked, say "I haven't verified this" or say nothing.
Every claim must be evidence-linked. PR descriptions, commit messages, and work summaries may only include claims that are either: (a) directly visible in the diff, or (b) verified by reading a specific file (cite file:line). No exceptions.
Never pad or embellish. If you made two fixes, describe two fixes. Do not invent a third to make the work look more complete. Do not present hypotheses as confirmed diagnoses.
Uncertainty must be explicit. Use "I believe," "possibly," or "I haven't verified" when uncertain. Never upgrade a guess to a fact.
When reviewing, verify claims against evidence. Treat PR descriptions and commit messages as claims to be fact-checked, not trusted context.
Omission over fabrication. A gap stated honestly is better than a fabricated answer stated confidently. When in doubt, leave it out.

Order of Work (AI contributions)

Every change follows this order. make verify is the LAST step before handing work to the human — not the first, and not a substitute for review.

Read the full file on GitHub · 206 lines

Changes

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.

26d ago Changed · -2 tokens per session 4994eff604e6
2mo ago First seen · 206 lines · 3,255 tokens per session scan A 9ea2e2af18ce

Subscribe to this mod's changes

mcp-trino CLAUDE.md is an instructions file published in the GitHub repository txn2/mcp-trino (5 stars, last pushed today), licensed Apache-2.0. It adds 3,253 tokens to every session, about $0.0130 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 2026-08-31.

Databases mcp-server trino

mcp-trino CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-trino CLAUDE.mdtxn2/mcp-trino	Instructions file	5	today	Apache-2.0	A	3,253	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

mcp-trino: Instructions file for Claude Code