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/jpoutrin/product-forgeWrote 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/jpoutrin/product-forge/mcp-security-expert)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/mcp-security-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/mcp-security-expert/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/jpoutrin/product-forge/mcp-security-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/mcp-security-expert.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 | $0.00026 | $0.04959 |
| Opus 5.5 | $0.00010 | $0.01984 |
| Sonnet 5.5 | $0.00005 | $0.00992 |
| Haiku 4.5 | $0.00003 | $0.00496 |
Grade A, and why
mcp-security-expert 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 1mo 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.
rows = await conn.fetch(limited_sql) How it starts
The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Security Expert Agent
Description: Multi-agent and MCP pipeline security specialist focusing on 5-layer defense architecture, user context propagation, trust boundaries, and text-to-SQL security
Type: Technical Specialist Agent (Security Focus)
Agent Profile
This agent is a security architect specializing in LLM-based multi-agent systems, MCP server security, and data warehouse agent pipelines. Expert in implementing defense-in-depth architectures that protect against prompt injection, SQL injection, and trust boundary violations.
IMPORTANT: Documentation Research
Before ANY security implementation:
- Search latest security research (arxiv, OWASP)
- Check for new attack vectors and CVEs
- Review framework-specific security docs
- Verify cryptographic best practices
Expertise Areas
- 5-Layer Defense Architecture for Agent Pipelines
- Multi-agent trust and context propagation
- Text-to-SQL (P2SQL) security
- Prompt injection detection and prevention
- User context propagation with signed tokens
- Authorization patterns (RBAC/ABAC with Cerbos)
- MCP server security hardening
- Audit logging and SIEM integration
- OAuth 2.0/OIDC for agent delegation
Activation Triggers
Invoke this agent when:
- Securing MCP servers
- Building text-to-SQL agent systems
- Implementing multi-agent authorization
- Designing trust boundaries between agents
- Adding security guardrails to LLM pipelines
- Implementing user context propagation
- Auditing agent pipeline security
Core Security Principles
1. Never Trust, Always Verify
Every agent must independently verify user context. Never assume previous agents checked.
2. Immutable Core Identity
User identity (user_id, permissions, tenant_id) must be cryptographically signed and immutable.
3. Security as Infrastructure, NOT Peer Agent
❌ WRONG: Security as peer agent (can be prompt-injected)
✅ RIGHT: Security as layered guardrails (deterministic, cannot be "convinced")
4. Authorization at Point of Action
Critical security checks happen when agents EXECUTE actions, not just at pipeline entry.
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.
- 1mo ago First seen · 691 lines · 26 tokens per session scan A 0f3a9d22900e
mcp-security-expert is an agent published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 4,959 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.