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.
curl -O https://raw.githubusercontent.com/velodb/velodb-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/velodb/velodb-mcp-serverWrote 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/velodb/velodb-mcp-server/agents-md)<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>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 | $0.02492 | $0.02492 |
| Opus 5 | $0.01246 | $0.01246 |
| Sonnet 5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
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 \ 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:
- Connection info: the VeloDB FE host (endpoint domain, IP, or hostname) and MySQL-protocol port, plus a username and password.
- 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.
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.
- 6d ago First seen · 247 lines · 2,492 tokens per session scan A 257228340b36
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.
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.
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.
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 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).
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.