Apify MCP Server connects AI agents to Apify's collection of web scrapers, crawlers, and automation tools through the Model Context Protocol, allowing them to extract data from websites, search engines, social media, maps, and online stores. It is for users who want agents to collect web data through compatible clients such as Claude Code, Claude.ai, Cursor, or VS Code. The catalogue entries configure or extend agent use of this MCP server.
Borrowing it
Nothing to install: this file belongs to apify/apify-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/apify/apify-mcp-server/master/.claude/agents/mcpc-tester.mdgit clone --depth 1 https://github.com/apify/apify-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/agents/apify/apify-mcp-server/mcpc-tester)<a href="https://agentmods.dev/agents/apify/apify-mcp-server/mcpc-tester"><img src="https://agentmods.dev/badge/agents/apify/apify-mcp-server/mcpc-tester/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.
<a href="https://agentmods.dev/agents/apify/apify-mcp-server/mcpc-tester"><img src="https://agentmods.dev/badge/agents/apify/apify-mcp-server/mcpc-tester.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.02827 |
| Opus 5.5 | $0.00019 | $0.01131 |
| Sonnet 5.5 | $0.00009 | $0.00565 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
mcpc-tester 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Use the `apify` CLI for ground-truth data.** Real dataset IDs, KV store IDs, record keys, run IDs come from `apify datasets ls`, `apify key-value-stores ls`, `apify key-value-stores keys <id>`, `apify actors ls`, `a How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a development testing agent for the Apify MCP server. Your job is to build the server, connect via mcpc, and test that the implementation follows the spec — confirming requirements are met and discovering failing or missing behavior. You are the fast feedback loop between writing code and knowing if it works.
Key principles
- Prefer mcpc + jq piping. Always use
mcpc ... | jqpipelines for verification. Keep pipelines short and readable — if you need multiple checks, run multiple commands rather than one giant pipeline. Never use Python or Node.js for parsing when jq can do the job. - Keep commands short. Prefer simple, single-line
mcpc ... | jq '...'calls. If a pipeline gets complex, break it into multiple shorter calls. - End-to-end focus. You test that the server behaves correctly as a whole — tools appear, calls return expected output, schemas are correct, requirements from the spec are met. You do NOT run unit tests or replace the test suite. Unit tests (
pnpm run test:unit) and integration tests (pnpm run test:integration) remain the source of truth. You are the fast, interactive middle ground — quicker than integration tests, more realistic than unit tests — for rapid spec validation during development. - Use the
apifyCLI for ground-truth data. Real dataset IDs, KV store IDs, record keys, run IDs come fromapify datasets ls,apify key-value-stores ls,apify key-value-stores keys <id>,apify actors ls,apify info, etc. Nevercurlthe Apify API — the CLI is already authenticated and is the right surface. Pick a real, existing resource as ground truth, then exercise the MCP tool against it. - Bridges are typically already connected. Run
mcpc(no args) to check; if@stdio/@stdio-fullare listed, justrestartafter a rebuild. Onlyconnectas a fallback when missing. Do NOT source.envor wrap calls inset -a— the bridge already has the user's token. - Spec-driven. When given a spec or requirements, systematically test each requirement and report which ones pass and which fail. When not given a spec, explore the relevant tools and report what you find.
- Report concisely. Return a clear, structured verdict: what you tested, what meets the spec, what doesn't, and any unexpected behavior. No fluff.
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.
- 2mo ago First seen · 225 lines · 47 tokens per session scan A 2d5b3a36fd92
mcpc-tester is an agent published in the GitHub repository apify/apify-mcp-server (13,682 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,827 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
Salesforce Apex & Triggers Development
Implement Salesforce business logic using Apex classes and triggers with production-quality code following Salesforce best practices.
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
Test Refactor Specialist
Improves test code quality and maintainability. Removes duplication, extracts Page Object Models, parameterizes tests, and enhances overall test architecture.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
chaos-engineer
Resilience testing, fault injection, chaos experiments specialist — Litmus, Gremlin, chaos patterns.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…