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.
npx skills add anilcancakir/laravel-agent-mcp --skill agent-mcp-cligit clone --depth 1 https://github.com/anilcancakir/laravel-agent-mcpWrote 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/anilcancakir/laravel-agent-mcp/agent-mcp-cli)<a href="https://agentmods.dev/skills/anilcancakir/laravel-agent-mcp/agent-mcp-cli"><img src="https://agentmods.dev/badge/skills/anilcancakir/laravel-agent-mcp/agent-mcp-cli/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/anilcancakir/laravel-agent-mcp/agent-mcp-cli"><img src="https://agentmods.dev/badge/skills/anilcancakir/laravel-agent-mcp/agent-mcp-cli.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 | $0.00175 | $0.01933 |
| Opus 5 | $0.00088 | $0.00966 |
| Sonnet 5 | $0.00035 | $0.00387 |
| Haiku 4.5 | $0.00017 | $0.00193 |
Grade A, and why
agent-mcp-cli 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 12d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent MCP CLI
Call the agent-mcp read-only tools straight from the shell, without registering an MCP server in the client. The CLI honors the same per-tool config flags, audit log, and best-effort redaction as the HTTP endpoint. Run commands with the project's artisan binary: examples use php artisan, but use the project's form where it differs (for example vendor/bin/sail artisan agent-mcp:call ...).
CLI or MCP server
- Use the CLI for a one-off call, a script, a CI job, or any context where the agent-mcp server is not registered in the client.
- Register the MCP server (the HTTP route or the stdio bridge) when you want persistent, low-latency tool access across many turns. The thesis: do not add an MCP server you only occasionally need; reach for the CLI instead, and register the server when the need is constant.
Workflow
- Discover:
php artisan agent-mcp:toolslists the callable tools (add--allto include tools disabled in config, flaggedenabled: false). - Inspect inputs:
php artisan agent-mcp:schema <tool>prints a tool's input schema. - Call: pass a JSON arguments object as a positional argument or on STDIN.
php artisan agent-mcp:call db_schema '{"table":"users"}'echo '{"table":"users"}' | php artisan agent-mcp:call db_schema
- Read the result: the JSON payload goes to stdout (pretty on a terminal, raw when piped, or force raw with
--raw); diagnostics go to stderr; the exit code is non-zero on a tool error. Pipe to a processor:php artisan agent-mcp:call db_schema --raw | jq ..
Local and remote
- Local (default): the command runs the tool in-process against the current app. Use it from inside the project or on the server.
- Remote: the command forwards to a remote
/agent-mcpendpoint and usesAGENT_MCP_KEYas a Bearer token. Remote mode is auto-selected when a remote URL is configured;--localand--remoteforce the choice. The key travels only in the Authorization header, never in output.
Configuring a remote URL
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 69 lines · 175 tokens per session scan A 256f43379779
agent-mcp-cli is a skill published in the GitHub repository anilcancakir/laravel-agent-mcp (5 stars, last pushed 2mo ago), licensed MIT. It adds 175 tokens to every session and 1,933 once invoked, about $0.0009 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.
Other skills, from other repositories
analyzing-browser-forensics-with-hindsight
Parse Chromium-based browser databases with Hindsight to extract and correlate browsing history, downloads, cookies, cached content, autofill data, saved passwords, and extensions from Chrome, Edge, Brave, Opera, and Vivaldi into a unified timeline (XLSX, JSON, or SQLite output). Use during incident response…
analyzing-browser-forensics-with-hindsight
Analyze Chromium-based browser artifacts using Hindsight to extract browsing history, downloads, cookies, cached content, autofill data, saved passwords, and browser extensions from Chrome, Edge, Brave, and Opera for forensic investigation.
hunt-cache-poison
Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai…
Cursor AI Testing Patterns
Effective test automation patterns with Cursor AI IDE including Composer for test suite generation, Cmd+K for inline test edits, Chat for test debugging, codebase-aware test generation, and rules configuration for testing conventions.
boutique-best-practices
Best practices for using Boutique with Swift 6 concurrency, @Observable, @ObservationIgnored, Sendable conformance, testing with preview stores, and dependency injection. Use when troubleshooting Boutique issues, migrating to Swift 6, or setting up tests.
boutique-store
Create and use Boutique Store for Swift data persistence, including initialization, @Stored controllers, CRUD operations, operation chaining, and granular event monitoring. Use when persisting arrays of items, building data controllers, or working with Boutique's Store type.