apify-mcp-server AGENTS.md

A contributor guide for the Apify MCP server, a service that lets coding tools communicate with Apify features. It covers communication style, project scope, Git practices, and required checks.

In plain words
What is it for?
Use it when planning a change, writing code or pull-request text, choosing a branch or commit format, adding tests, or preparing an Apify server contribution.
Why use it?
It helps contributors make focused, reviewable changes and follow the project's required issue, testing, and disclosure process.

Instructions file for CodexOpenCode

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/apify/apify-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/apify/apify-mcp-server

Made for: Codex, OpenCode.

Per session 2,347 This file is loaded in full into every session.
When invoked 2,347 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.02347 $0.02347
Opus 5 $0.01174 $0.01174
Sonnet 5 $0.00469 $0.00469
Haiku 4.5 $0.00235 $0.00235

Measured 2d ago against content hash 58747f84ade5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apify-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 2d 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.

When the user says "test with mcpc", **use mcpc** — do not invent a substitute (no curl, no ad-hoc Node/Python scripts, no unit tests in place of an e2e probe). Use the **apify CLI** (`apify datasets`, `apify key-value-s
AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apify MCP server

TypeScript, ES modules. Runs in two modes: stdio (local CLI clients, stdio.ts) and HTTP Streamable (dev_server.ts).

Before implementing: work from an issue that is assigned or explicitly agreed. An open issue is not an invitation — many are stale or unrefined, and the fix isn't settled. If nobody asked for this change, open an issue instead of a PR (docs fixes excepted). Disclose AI use in the PR; never add a model as co-author. See CONTRIBUTING.md.

Communication style — MANDATORY

This applies to ALL written output: code comments, commit messages, PR descriptions, issue specs

  • Plain language, no fluff. Say what you mean in the fewest words. No filler phrases, no motivational preambles, no "this will improve the developer experience."

Scope discipline

  • Minimal. Implement only what's explicitly requested. No speculative features, no hypothetical future-proofing — solve the current problem, not imagined ones.
  • One thing per change. Bug fix fixes only the bug — no cleanup, no renames, no drive-by refactors. Mention unrelated issues; don't fix them.
  • Test first for bug fixes. Write a failing test that reproduces the bug, confirm it fails, then fix.
  • Refactoring is a separate PR. If a feature needs refactoring, land the refactor first, then the feature. Never mix.
  • Fix by adjusting, not adding. Prefer a 1-line fix over a 10-line fix. Prefer adjusting existing code over adding new branches. Search for existing helpers and patterns that already handle similar cases. Ask: "Am I adding code, or fixing the code that's already there?"
  • Self-review your diff. Before declaring done, review: Is this the minimal fix? Am I reusing existing patterns? Did I leave any debug artifacts?

Git: branch names, commits, PR titles

Conventional Commits for all three. Branch: type/short-desc (e.g. fix/connection-timeout). Commit/PR title: type: Description (e.g. fix: Handle connection errors). Types: feat, fix, chore, refactor, docs, test. Append ! for breaking changes. PR title ≤70 chars.

Read the full file on GitHub · 96 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. 2d ago First seen · 96 lines · 2,347 tokens per session scan A 58747f84ade5

Subscribe to this mod's changes

apify-mcp-server AGENTS.md is an instructions file published in the GitHub repository apify/apify-mcp-server (5,636 stars, last pushed yesterday), licensed MIT. It adds 2,347 tokens to every session, about $0.0117 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 2026-08-30.