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.
git clone --depth 1 https://github.com/OutSystems/outsystems-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/plugins/outsystems/outsystems-mcp/claude)<a href="https://agentmods.dev/plugins/outsystems/outsystems-mcp/claude"><img src="https://agentmods.dev/badge/plugins/outsystems/outsystems-mcp/claude/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/plugins/outsystems/outsystems-mcp/claude"><img src="https://agentmods.dev/badge/plugins/outsystems/outsystems-mcp/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
outsystems 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 today.
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.
What it actually says
{
"name": "outsystems",
"displayName": "OutSystems - MCP",
"description": "Edit, publish, deploy, and search OutSystems apps, and manage external libraries, from your AI assistant. Connects to your own OutSystems tenant's MCP server over OAuth.",
"version": "1.7.0",
"author": {
"name": "OutSystems AI Platform",
"url": "https://www.outsystems.com"
},
"keywords": [
"outsystems",
"odc",
"outsystems developer cloud",
"odc studio",
"oml",
"outsystems mentor"
],
"license": "MIT",
"homepage": "https://github.com/OutSystems/outsystems-mcp",
"repository": "https://github.com/OutSystems/outsystems-mcp",
"icon": "./.claude-plugin/icon.png",
"documentationUrl": "https://github.com/OutSystems/outsystems-mcp#readme",
"supportUrl": "https://github.com/OutSystems/outsystems-mcp/issues",
"privacyPolicyUrl": "https://www.outsystems.com/legal/terms-of-use/privacy-statement",
"termsOfServiceUrl": "https://www.outsystems.com/legal/outsystems-msa/master-subscription-agreement",
"skills": "./skills/",
"commands": "./commands/",
"userConfig": {
"tenant_hostname": {
"type": "string",
"title": "OutSystems tenant hostname",
"description": "The host part of your OutSystems URL, for example mycompany.outsystems.dev. No https://, no path.",
"required": true
}
}
}
What it installs
The manifest is a name and a version. 6 skills, 1 command, 1 agent, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 1,142 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill outsystems-design-to-app A 222 tokens
- Skill outsystems-app-architecture A 199 tokens
- Skill outsystems-tenant-architecture A 216 tokens
- Skill outsystems-dependency-impact A 185 tokens
- Skill outsystems-spec-driven-build A 219 tokens
- Skill outsystems B 30 tokens
- Command outsystems-feedback A 0 tokens
- Agent status-watcher A 71 tokens
- Hook PreToolUse A not measured
- MCP server outsystems A not measured
What ships with it
1 file beside plugin.json 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.
- today Changed 9f5806368fe3
- yesterday Changed 6c0aea342173
- 4d ago Changed 9c8b58f4bca3
- 6d ago Changed 0c891de3c690
- 7d ago Changed 7f0345c19dfb
- 11d ago Changed ad4106de8833
- 12d ago Changed bd252bbc6f94
- 13d ago Changed 985932c1a715
- 14d ago First seen · 37 lines scan A 7a63a12fbd31
outsystems is a plugin published in the GitHub repository OutSystems/outsystems-mcp (40 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-30.
Other plugins, from other repositories
claudehut
Claude Code workflow for Java/Spring Boot backends: routes each request direct, light or full; advisory hooks that never block; a deterministic codebase index with a microservice knowledge hub; review lanes chosen from the diff.
api-authentication
Secure API authentication with JWT, OAuth 2.0, API keys. Use for authentication systems, third-party integrations, service-to-service communication, or encountering token management, security headers, auth flow errors.
csrf-protection
Implements CSRF protection using synchronizer tokens, double-submit cookies, and SameSite attributes. Use when securing web forms, protecting state-changing endpoints, or implementing defense-in-depth authentication.
fuse-php
Expert modern PHP 8.5/8.4 for non-Laravel projects — libraries, standalone Symfony components, Slim, API-first apps, and CLI tools, with PER Coding Style 3.1, PHPStan, and SOLID principles.
elliot marketplace
Turn any API or database into agent-ready MCP tools. The Elliot marketplace ships the platform plugin (10 skills + MCP server + connector templates).
essential8
Essential 8 Plugin - Australian Cyber Security Centre mitigation strategies with 3 maturity levels.