Borrowing it
Nothing to install: this file belongs to getmasv/masv-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/getmasv/masv-mcp-server/main/.kiro/steering/architecture.mdgit clone --depth 1 https://github.com/getmasv/masv-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/instructions/getmasv/masv-mcp-server/architecture)<a href="https://agentmods.dev/instructions/getmasv/masv-mcp-server/architecture"><img src="https://agentmods.dev/badge/instructions/getmasv/masv-mcp-server/architecture/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/instructions/getmasv/masv-mcp-server/architecture"><img src="https://agentmods.dev/badge/instructions/getmasv/masv-mcp-server/architecture.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 | $0.00996 | $0.00996 |
| Opus 5.5 | $0.00398 | $0.00398 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
masv-mcp-server architecture.md 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 26d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Principles
Control plane / data plane split
Non-negotiable. The MCP server exchanges references, IDs, manifests, status, and policy — never bytes.
agent / workflow
│ intent, manifest, policy
▼
MASV MCP control plane ──────► MASV data plane
▲ ├── MASV Agent / Desktop (local disk, NAS)
│ status, events ├── Browser SDK / portal
└────────────────────── └── connected cloud storage
Consequences that constrain every change:
- Never return or stream file content through a tool result.
- The server must stay filesystem-free. It only calls
MASV_BASE_URLover HTTPS. Local files are reached through Storage Gateway, an out-of-band daemon on the user's machine. This is what lets the same codebase run locally or hosted remotely with only a transport change. Do not break it. - Long operations return an operation ID and are polled or webhooked. Never block on a transfer.
Transport
- Today: stdio. Target: HTTP, publicly reachable.
- stdio does not run in remote agent sessions and is not listable on ChatGPT or M365. Keep stdio and the MCPB bundle for developers, but the remote server is the strategic artifact.
- Build against the stateless MCP core (2026-07-28 spec). No session-affine state.
Authorization belongs to MASV, not to this client
The MASV API is the authority on what a caller may do. The API key carries the user's own permissions, so access management is configured in MASV — not by adding checks here.
Keep this client thin:
- Do not build permission, quota, budget, or policy engines here. They would duplicate backend behaviour, drift from it, and be bypassable by calling the API directly. A control that only exists in a client is not a control.
- Do not add config switches speculatively.
MASV_ALLOW_DELETEexists as a deliberate guard on two irreversible operations. Treat it as the exception, not a pattern to extend. Add more only with evidence that users need them. - Surface what the API says. When MASV rejects a call on permissions or limits, pass that through as a clear, actionable message instead of pre-empting it with local logic.
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.
- 26d ago First seen · 83 lines · 996 tokens per session scan A c1269ebcacb6
masv-mcp-server architecture.md is an instructions file published in the GitHub repository getmasv/masv-mcp-server (5 stars, last pushed 21d ago), licensed MIT. It adds 996 tokens to every session, about $0.0040 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 2026-09-25.
Other instructions, from other repositories
vibetags com-example-service-NewAnnotationsShowcase-DraftKafkaIntegrationSpike.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for draftkafkaintegrationspike and experimental prototype.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).