Threat Modeling MCP Server is an MCP server that guides an AI coding agent through structured security threat modeling and code validation. It analyzes business context, architecture, assets, trust boundaries, and threat actors, then produces Markdown or JSON reports using a phased STRIDE-based process. The catalogue skills operate this workflow through compatible agent clients.
Borrowing it
Nothing to install: this file belongs to awslabs/threat-modeling-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/awslabs/threat-modeling-mcp-server/main/.kiro/skills/phase-4-trust-boundaries/SKILL.mdgit clone --depth 1 https://github.com/awslabs/threat-modeling-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/awslabs/threat-modeling-mcp-server/phase-4-trust-boundaries)<a href="https://agentmods.dev/skills/awslabs/threat-modeling-mcp-server/phase-4-trust-boundaries"><img src="https://agentmods.dev/badge/skills/awslabs/threat-modeling-mcp-server/phase-4-trust-boundaries/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/awslabs/threat-modeling-mcp-server/phase-4-trust-boundaries"><img src="https://agentmods.dev/badge/skills/awslabs/threat-modeling-mcp-server/phase-4-trust-boundaries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.00959 |
| Opus 5.5 | $0.00013 | $0.00384 |
| Sonnet 5.5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
phase-4-trust-boundaries 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 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.
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 4: Trust Boundary Analysis
Objective
Identify where trust levels change in the system. Every crossing point is a potential attack surface that needs security controls.
Trust-boundary state starts empty. Define zones, crossing points, and boundaries for the system under review before advancing.
Concepts
- Trust Zone: A region where components and data stores share the same trust level
- Crossing Point: Where data flows between zones (requires authentication/authorization)
- Trust Boundary: The security perimeter with specific controls
Tools Reference
Start with manage_trust_boundaries(action="describe", section=SECTION) for the
exact contract.
manage_trust_boundaries(action="add", section="zones", values=ZONE)
| Parameter | Values |
|---|---|
| trust_level | Untrusted, Low, Medium, High, Full |
manage_trust_boundaries(action="link", section="zones", values=LINK)
Assign an architecture node to exactly one trust zone. The link fields are
zone_id and node_id; a node may be either a component or a data store.
manage_trust_boundaries(action="add", section="crossing_points", values=CROSSING)
| Parameter | Values |
|---|---|
| authentication_method | Password, Multi-factor, Certificate, Token, Biometric, API Key, IAM Role, OAuth, None, Other |
| authorization_method | Role-based, Attribute-based, Discretionary, Mandatory, Policy-based, Rule-based, None, Other |
manage_trust_boundaries(action="link", section="crossing_points", values=LINK)
Map existing connections to crossing points.
manage_trust_boundaries(action="add", section="boundaries", values=BOUNDARY)
| Parameter | Values |
|---|---|
| type | Network, Process, Physical, Container, Virtual Machine, Account, Other |
| crossing_point_ids | List of crossing point IDs |
| controls | List of security control names (strings) |
Other Phase 4 Tools
manage_trust_boundaries(action="list", section="all")-- Review the complete modelmanage_trust_boundaries(action="detection_plan", section="all")-- AI-powered boundary detectionmanage_trust_boundaries(action="analysis_plan", section="all")-- Security analysis guidance- CRUD actions accept
valuesfor one record anditemsfor a batch
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 · 98 lines · 32 tokens per session scan A 7da90033f365
phase-4-trust-boundaries is a skill published in the GitHub repository awslabs/threat-modeling-mcp-server (120 stars, last pushed 5d ago), licensed Apache-2.0. It adds 32 tokens to every session and 959 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…