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/skills/bug-triage/SKILL.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/skills/apify/apify-mcp-server/bug-triage)<a href="https://agentmods.dev/skills/apify/apify-mcp-server/bug-triage"><img src="https://agentmods.dev/badge/skills/apify/apify-mcp-server/bug-triage/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/skills/apify/apify-mcp-server/bug-triage"><img src="https://agentmods.dev/badge/skills/apify/apify-mcp-server/bug-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 86 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- high Tool Misuse · line 88 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 88 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 88 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 88 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00056 | $0.01685 |
| Opus 5.5 | $0.00022 | $0.00674 |
| Sonnet 5.5 | $0.00011 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade C, and why
bug-triage scanned grade C 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
4. **npx cache corruption**: Stale cache prevents stdio server from starting. Fix: `rm -rf ~/.npm/_npx` (macOS/Linux) or `rmdir /s /q %LOCALAPPDATA%\npm-cache\_npx` (Windows). How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Triage
Triage open bug issues on apify/apify-mcp-server. Analyze, draft responses, get approval, post.
Permissions
- Read-only by default: listing issues (
gh issue list), viewing details and comments (gh issue view) — do these automatically, no need to ask. - Write requires approval: commenting (
gh issue comment), closing (gh issue close), editing (gh issue edit) — always present the draft and wait for explicit user approval before executing.
Step 0: Parse arguments
$ARGUMENTS controls scope:
| Input | Behavior |
|---|---|
623 641 639 |
Triage specific issue numbers |
--label bug |
Triage all open issues with label (default: bug) |
--all |
Triage all open bug-labeled issues |
| (empty) | Same as --all |
Step 1: Fetch issues
Use the arguments parsed in Step 0 to determine what to fetch.
If specific issue numbers were provided, skip the list queries and fetch each issue directly:
gh issue view <number> --repo apify/apify-mcp-server --comments
Otherwise (label mode, --all, or empty), fetch open bug reports. Use the label from Step 0 (default: bug). Bug reports come in two forms — find both:
- By label: issues with the parsed label
- By title prefix: issues with
[Bug]in the title (the bug report template adds this, but the label isn't always applied)
# By label (use the label from Step 0, default: bug)
gh issue list --repo apify/apify-mcp-server --label <label> --state open --json number,title,labels,createdAt,body --limit 30
# By title prefix (catches unlabeled bug reports)
gh issue list --repo apify/apify-mcp-server --state open --search "[Bug] in:title" --json number,title,labels,createdAt,body --limit 30
Merge both lists and deduplicate by issue number.
For each issue, fetch full details including all comments (comments often contain the real context):
gh issue view <number> --repo apify/apify-mcp-server --comments
Always read comments before drafting a response. Previous team members may have already replied, asked for details, or provided workarounds. Don't duplicate existing responses.
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 · 148 lines · 56 tokens per session scan C a020404b69ce
bug-triage is a skill published in the GitHub repository apify/apify-mcp-server (13,682 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,685 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflows
Inspect and troubleshoot Prefect workflows, deployments, work pools, and releases with Prefect MCP tools. Use for Prefect operational questions, failure diagnosis, documentation lookup, and safe guidance when a requested mutation requires a separately configured Prefect CLI.
incident-rca
Walk a data incident from symptom to root cause: correlate the anomaly, trace the failing upstream job, and produce a root-cause narrative with the evidence chain.
unity-runtime-performance
Use for runtime performance triage from the project filesystem: quality tiers, graphics/URP-HDRP settings, lighting, large assets, scene complexity proxies, and build-size hotspots (no Editor Profiler required).
unity-broken-refs-triage
Use when prefabs/scenes show Missing Script or pink materials: triage broken script and asset GUID references and decide fix order.
unity-memory-asset-pressure
Use to find memory/disk pressure from assets: large files, textures, audio, video, ML models, and Addressables that should be remote.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.