What is cubrid-mcp-server AGENTS.md?

Repository instructions for cubrid-mcp-server, an MCP server for the CUBRID database that supports schema inspection and read-only queries.

Use them when developing or maintaining the Python server, its database connection, schema tools, query explanations, health checks, or read-only safety checks.

They explain the project structure, coding requirements, and safety rules, including keeping database operations read-only and reserving standard output for the MCP protocol.

How cubrid-lab/cubrid-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to cubrid-lab/cubrid-mcp-server. 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/cubrid-lab/cubrid-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/cubrid-lab/cubrid-mcp-server

Made for: Codex, OpenCode.

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/cubrid-lab/cubrid-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/cubrid-lab/cubrid-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cubrid-lab/cubrid-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cubrid-lab/cubrid-mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cubrid-lab/cubrid-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cubrid-lab/cubrid-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,039 This file is loaded in full into every session.

When invoked 6,039 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	$0.06039	$0.06039
Opus 5.5	$0.02416	$0.02416
Sonnet 5.5	$0.01208	$0.01208
Haiku 4.5	$0.00604	$0.00604

Measured 7d ago against content hash 23c050eb0c10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cubrid-mcp-server 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 7d 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.

AGENTS.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Organization-wide writing standard

Issue titles use type only (such as feat: ..., bug: ...), with no required module scope. Explain a clear human-readable problem or goal and verifiable acceptance criteria; separate verified observations from assumptions and omit personal comments/internal IDs. Triage evaluates validity, duplication, scope, priority and size; PRs/commits follow local Conventional Commits and existing PR validation gates. See cubrid-lab's writing standard.

Guidance for AI agents and contributors working in this repository.

Project Overview

cubrid-mcp-server is a Model Context Protocol server for the CUBRID database. It lets LLM clients safely inspect schemas and run read-only queries via the pure-Python pycubrid driver, with an opt-in, separately registered write tool.

Package: cubrid_mcp_server/
Entry points: cubrid-mcp-server console script or python -m cubrid_mcp_server
Tool, resource and prompt surface: docs/TOOLS.md is authoritative (schema inspection, index/serial/class-hierarchy listing, explain_query, table_row_counts, read-only execute_query, health_check, and execute_write only when write mode is enabled). Security boundaries: docs/SECURITY_MODEL.md.

Architecture

cubrid_mcp_server/
├── server.py     # MCP server: tools, resources, prompts
├── database.py   # pycubrid connection + query execution
├── safety.py     # read-only SQL enforcement / whitelist, write-mode checks
├── audit.py      # opt-in, redacted stderr audit log (CUBRID_MCP_AUDIT_LOG)
├── config.py     # environment-variable configuration
├── context.py    # request/connection context
├── __main__.py   # module / console-script entry point
└── py.typed      # PEP 561 marker

Read the full file on GitHub · 414 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.

7d ago Changed · +53 lines · +723 tokens per session 23c050eb0c10
11d ago Changed · +4 lines · +119 tokens per session fb9471dbd6fe
12d ago Changed · +25 lines · +340 tokens per session a41a85f98ba0
14d ago Changed · -10 lines · -194 tokens per session 663a34c4dacb
15d ago Changed · +7 lines · +161 tokens per session c04c12ceda2e
21d ago Changed · +1 lines · +40 tokens per session 42c11ac5bdca
22d ago Changed · +30 lines · +535 tokens per session 283009984552
23d ago Changed · +192 tokens per session 0f67264fba39
25d ago Changed · +8 lines · +183 tokens per session 4421be720529
26d ago First seen · 296 lines · 3,940 tokens per session scan A 96ff476e826b

Subscribe to this mod's changes

cubrid-mcp-server AGENTS.md is an instructions file published in the GitHub repository cubrid-lab/cubrid-mcp-server (34 stars, last pushed 2d ago), licensed MIT. It adds 6,039 tokens to every session, about $0.0242 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.

Databases ai-agents asyncio cubrid cubrid-database fastmcp

cubrid-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cubrid-mcp-server AGENTS.mdcubrid-lab/cubrid-mcp-server	Instructions file	34	2d ago	MIT	A	6,039	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cubrid-mcp-server: Instructions file for Codex