What is dokploy-mcp AGENTS.md?

Project instructions for an MCP server that connects AI coding agents to the Dokploy hosting API. They describe its TypeScript structure, code style, testing, and development rules.

Reviewing Dokploy MCP server code, locating its tools and generated files, following its formatting rules, and running the expected tests.

They give an agent the project context needed to review or change the code consistently, without having to infer the architecture and conventions.

dokploy-mcp AGENTS.md — Instructions file by vcode-sh

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/vcode-sh/dokploy-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/vcode-sh/dokploy-mcp

Made for: Codex, OpenCode.

Per session 647 This file is loaded in full into every session.

When invoked 647 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00647	$0.00647
Opus 5	$0.00324	$0.00324
Sonnet 5	$0.00129	$0.00129
Haiku 4.5	$0.00065	$0.00065

Measured yesterday against content hash 582d10a61d78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dokploy-mcp 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 yesterday.

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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md -- project context for AI code review

What this is

MCP (Model Context Protocol) server for the Dokploy API. v2 is Code Mode only: three public tools: search, execute, and list_profiles, backed by generated OpenAPI artifacts, a sandboxed runtime, and a generated Dokploy SDK. TypeScript, ES modules, Node >= 24.

Architecture

Entry: src/index.ts (CLI vs MCP server)
Server: src/server.ts (registers Code Mode tools with McpServer)
Public tools: src/codemode/tools/search.ts, src/codemode/tools/execute.ts, src/codemode/tools/list-profiles.ts
Tool factory: src/mcp/tool-factory.ts
Search context: src/codemode/context/search-context.ts
Execute context: src/codemode/context/execute-context.ts
Gateway: src/codemode/gateway/*.ts
Sandbox: src/codemode/sandbox/*.ts
Generated artifacts: src/generated/*
Config: src/config/resolver.ts (env vars > config file > Dokploy CLI config)
CLI: src/cli/setup.ts (interactive wizard using @clack/prompts)

Code style

Formatter/linter: Biome (not ESLint/Prettier)
Single quotes, no semicolons, trailing commas, 2-space indent, 100 char line width
kebab-case filenames (enforced by Biome)
useConst, useTemplate, useImportType, useExportType -- all enforced
No forEach -- use for...of or .map()
No enums -- use const objects or union types
Max cognitive complexity: 20

Testing

Framework: Vitest
Tests in tests/*.test.ts
Coverage: v8 provider, excludes entry shims src/index.ts, src/cli/index.ts, and generated code
Run: npm test or npm run test:coverage

Commands

npm run build        # tsc
npm run typecheck    # tsc --noEmit
npm run lint         # biome check .
npm run lint:fix     # biome check --write .
npm test             # vitest run
npm run test:coverage # vitest run --coverage

Dependencies

Runtime: @modelcontextprotocol/sdk, zod (v4), @clack/prompts
Dev: @biomejs/biome, vitest, typescript

Read the full file on GitHub · 61 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.

yesterday First seen · 61 lines · 647 tokens per session scan A 582d10a61d78

Subscribe to this mod's changes

dokploy-mcp AGENTS.md is an instructions file published in the GitHub repository vcode-sh/dokploy-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 647 tokens to every session, about $0.0032 per session on Opus 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.

Backend and APIs Code review Testing cli deployment docker dokploy infrastructure

ecspresso CLAUDE.md

Instructions for kayac/ecspresso, covering claude.md, project overview, git workflow, build commands and build the binary.

kayac/ecspresso · 931 tokens

piper CLAUDE.md

Instructions for piperbox/piper, covering claude.md, what this is, coding principles, 1. think before coding and 2. simplicity first.

piperbox/piper · 2,684 tokens

piper AGENTS.md

Instructions for piperbox/piper: Read CLAUDE.md in full first — it is the authoritative source for coding principles, commands, constraints, layering, and branch/PR/issue workflow. This file only captures high-signal facts an agent would otherwise get wrong that aren't obvious from filenames or CLAUDE.md.

piperbox/piper · 385 tokens

dokploy-mcp AGENTS.md