velodb-mcp-server: Instructions file for Codex

AGENTS.md

velodb-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from velodb/velodb-mcp-server. It costs 2,492 tokens per session, scanned A, original, Apache-2.0.

Agent instructions for installing the VeloDB MCP server and connecting it to a VeloDB cluster. A cluster is a group of servers working together as one database system.

In plain words
What is it for?
Automating VeloDB MCP setup, including collecting connection details, downloading the right release, configuring the FE address, and starting the server.
Why use it?
They tell a coding agent which questions to ask, how to choose a release, configure the server, check its health, and register it.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is velodb/velodb-mcp-server's own configuration. It tells Codex and OpenCode how to work on velodb-mcp-server 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 velodb-mcp-server configures →

Reuse

Borrowing it

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

agentmods badge for velodb-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/velodb/velodb-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/velodb/velodb-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/velodb/velodb-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/velodb/velodb-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,492 This file is loaded in full into every session.
When invoked 2,492 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02492 $0.02492
Opus 5 $0.01246 $0.01246
Sonnet 5 $0.00498 $0.00498
Haiku 4.5 $0.00249 $0.00249

Measured 6d ago against content hash 257228340b36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

velodb-mcp-server AGENTS.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://api.github.com/repos/<owner>/<repo>/releases/latest \
AGENTS.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Agent Playbook for Installing velodb-mcp-server

Audience: AI agents (Claude Code, Cursor, Codex, etc.), not humans. When a user asks you to install this MCP server and connect their VeloDB cluster, follow this playbook exactly. The user should never need to read any documentation — you do all the work; the user only answers a few questions.

Trigger phrases

The user may say something like:

  • "Install this MCP server per the README and tell me how to connect my VeloDB cluster."
  • "Set up the VeloDB MCP for me."
  • Any equivalent phrasing in any language (e.g. a Chinese request such as "install this MCP and tell me how to connect my VeloDB cluster")

If the request mentions installing/setting up this MCP server or connecting a VeloDB cluster, you are in the right place. Read this whole file first, then execute the steps in order.

Overview of what you will do

Step 0  Ask the user 2 short questions (connection info, install location)
Step 1  Detect the platform and download the matching release tarball
Step 2  Write the VeloDB FE address into mcp-server.toml
Step 3  Start the server in the background and health-check it
Step 4  Register the MCP server with the user's AI client (e.g. Claude Code)
Step 5  Verify end-to-end and report success

Do not skip steps. Verify each step before moving on. If a step fails, consult the Failure handling table.


Step 0 — Collect information (ask once, then proceed)

Ask the user exactly these questions (in one message), then wait for the answers:

  1. Connection info: the VeloDB FE host (endpoint domain, IP, or hostname) and MySQL-protocol port, plus a username and password.
  2. Install location: on this machine (where you are running), or on a remote server? If remote, ask how you can reach it (e.g. SSH access).

Rules:

  • VeloDB Cloud, VeloDB Enterprise, and Apache Doris all speak the same MySQL protocol, so this server connects to any of them the same way — do not ask which deployment type the user has; you only need the FE address and credentials.
  • The default MySQL-protocol port is 9030. Do not ask about it separately; only confirm if the user gave a non-default port.
  • The machine running this MCP server must be able to reach the FE host:9030. If the FE address is a private IP and the user wants to install on a laptop that cannot reach it, tell them and ask for a reachable install location instead.
  • Never print the user's password back in chat output beyond what is necessary to complete the setup commands.

Read the full file on GitHub · 247 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. 6d ago First seen · 247 lines · 2,492 tokens per session scan A 257228340b36

Subscribe to this mod's changes

velodb-mcp-server AGENTS.md is an instructions file published in the GitHub repository velodb/velodb-mcp-server (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,492 tokens to every session, about $0.0125 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens