agentmods.dev

mcp-blueprint: Instructions file for Codex

AGENTS.md

mcp-blueprint AGENTS.md is an instructions file for Codex, OpenCode from meob/mcp-blueprint. It costs 688 tokens per session, scanned A, original, Apache-2.0.

A repository guide describing the MCP servers in mcp-blueprint, including their tool naming, connection method, database engine, and target database.

In plain words
What is it for?
Use it when working with the project’s PostgreSQL, MySQL, Oracle, ClickHouse, SQL Server, or MariaDB MCP servers and their local or containerized databases.
Why use it?
It helps an AI assistant route database work to the correct server and identify which database environment a tool will use.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is meob/mcp-blueprint's own configuration. It tells Codex and OpenCode how to work on mcp-blueprint itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-blueprint configures →

not rated 0repo 2mo ago A scan 688 tokens original Apache-2.0
View source ↗ meob/mcp-blueprint
Reuse

Borrowing it

Nothing to install: this file belongs to meob/mcp-blueprint. 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/meob/mcp-blueprint/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/meob/mcp-blueprint

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.

agentmods badge for mcp-blueprint AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/meob/mcp-blueprint/agents-md/github.svg)](https://agentmods.dev/instructions/meob/mcp-blueprint/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/meob/mcp-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/meob/mcp-blueprint/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.

agentmods 80×15 button for mcp-blueprint AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/meob/mcp-blueprint/agents-md"><img src="https://agentmods.dev/badge/instructions/meob/mcp-blueprint/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 688 This file is loaded in full into every session.
When invoked 688 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00688 $0.00688
Opus 5.5 $0.00275 $0.00275
Sonnet 5.5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 2mo ago against content hash a5cf1d51421f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-blueprint 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 2mo 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Servers

This project exposes several MCP Blueprint servers. Each server name is prefixed to its tool names (e.g. pg-dba-docker_get_connections), so the server a tool runs against is always identifiable from the tool name.

Server Transport Engine Pack Target database
pg-dba stdio PostgreSQL pg-dba Local pgbench database on localhost:5432
pg-sakila stdio PostgreSQL sakila Local sakila database on localhost:5432
mysql-dba stdio MySQL mysql-dba Local mysakila database on localhost:3306
mysql-dba-docker stdio MySQL mysql-dba Containerized MySQL 8 mysakila on localhost:3308
pg-dba-docker remote PostgreSQL pg-dba Containerized PostgreSQL 16 (docker compose stack)
oracle-dba stdio Oracle oracle-dba Containerized Oracle 23 (PDB FREEPDB1) on localhost:1521
clickhouse-dba stdio ClickHouse clickhouse-dba Containerized ClickHouse 24.8 on localhost:9000
sqlserver-dba stdio SQL Server sqlserver-dba Containerized SQL Server 2022 on localhost:1433
mariadb-dba stdio MariaDB mariadb-dba Containerized MariaDB 11.4 mysakila on localhost:3307
smoke stdio SQLite smoke In-memory SQLite database (no external server)

Routing rules

  • Always call the tool whose server prefix matches the target environment.
  • "the Docker / containerized database" -> use pg-dba-docker_* tools.
  • "the local PostgreSQL / localhost" -> use pg-dba_* tools.
  • "the local MySQL / localhost" -> use mysql-dba_* tools.
  • "the containerized MySQL / 3308" -> use mysql-dba-docker_* tools.
  • Sakila store questions -> use pg-sakila_* tools.
  • MySQL questions -> use mysql-dba_* tools.
  • Oracle container questions -> use oracle-dba_* tools.
  • ClickHouse container questions -> use clickhouse-dba_* tools.
  • SQL Server container questions -> use sqlserver-dba_* tools.
  • MariaDB container questions -> use mariadb-dba_* tools.
  • "the smoke / deployment test server" -> use smoke_* tools (smoke_ping, smoke_get_server_status, smoke_fortune, smoke_horoscope).
  • When the target is ambiguous, ask which server to use instead of guessing.

Read the full file on GitHub · 36 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.

  1. 2mo ago First seen · 36 lines · 688 tokens per session scan A a5cf1d51421f

Subscribe to this mod's changes

mcp-blueprint AGENTS.md is an instructions file published in the GitHub repository meob/mcp-blueprint (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 688 tokens to every session, about $0.0028 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.

Related

mcp-blueprint AGENTS.md compared with instructions from other repositories

mcp-blueprint AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-blueprint AGENTS.mdmeob/mcp-blueprintInstructions file02mo agoApache-2.0A688Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode