A development guide for MCP integrations in VMark. MCP is a way for an application to connect to external tools and services through defined interfaces.

Adding or updating MCP servers and clients, configuring MCP tools, and updating MCP-related settings and documentation in VMark.

It helps keep server settings, client behavior, related documentation, and local configuration aligned while MCP work is being changed.

How xiaolai/vmark configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to xiaolai/vmark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/xiaolai/vmark/main/.claude/skills/mcp-dev/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/xiaolai/vmark

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xiaolai/vmark/mcp-dev/github.svg)](https://agentmods.dev/skills/xiaolai/vmark/mcp-dev)

Your own site

<a href="https://agentmods.dev/skills/xiaolai/vmark/mcp-dev"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/mcp-dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xiaolai/vmark/mcp-dev"><img src="https://agentmods.dev/badge/skills/xiaolai/vmark/mcp-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 627 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00065	$0.00627
Opus 5.5	$0.00026	$0.00251
Sonnet 5.5	$0.00013	$0.00125
Haiku 4.5	$0.00006	$0.00063

Measured yesterday against content hash 332c9b657cb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-dev 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan_mcp.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/mcp-dev/SKILL.md · 43 lines

What it actually says

MCP Dev (VMark)

Where things live

Layer	Path
Sidecar (npm package, stdio MCP server, tool definitions)	`server/mcp/` — tools in `server/mcp/src/tools/`
Payload schemas (single source)	`server/mcp/src/bridge/operationSchemas.ts`
Rust bridge and client config	`src-tauri/src/mcp_bridge/` (`control.rs` is the entry), `src-tauri/src/mcp_config/`
Frontend bridge	`src/services/mcpBridge/` — `handleRequest.ts` → `v2/dispatch.ts`
Docs	`website/guide/mcp-tools.md`, `website/guide/mcp-setup.md`, `server/mcp/README.md`

Changing a tool

Edit the zod schema in operationSchemas.ts, then pnpm gen:mcp-contracts and commit the generated files (pnpm lint:mcp-contracts fails on stale or hand-edited output).
Handlers follow .claude/rules/50-codebase-conventions.md §4: wrapHandler(id, async () => …), respond() on success, structuredError() for validation, readOperationArgs() for payloads.
Update the docs in the same change (.claude/rules/21-website-docs.md).
After sidecar changes: pnpm --dir server/mcp build:sidecar, reconfigure the client, restart it. E2E for AI features goes through VMark MCP only (tauri-mcp-testing skill).

Registering an MCP server

Project scope: edit .mcp.json. It registers exactly one server, tauri (npx -y @hypothesi/tauri-mcp-server), for driving a debug build. Never add Chrome DevTools MCP — VMark is a Tauri app.
User scope: claude mcp add <name> -- <command> <args…> (add -e KEY=VALUE for env), claude mcp remove <name>; verify with claude mcp list.
A url key means an HTTP server, command/args a stdio one. Servers load at session start, so the user must restart the session to pick one up.
Never commit credentials into .mcp.json; a VMark MCP client authenticates with its per-client VMARK_MCP_TOKEN.

Files

What ships with it

2 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.

Changes

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.

yesterday Changed · +23 lines · +32 tokens per session 332c9b657cb9
2mo ago First seen · 20 lines · 33 tokens per session scan A c7e9564bf6a3

Subscribe to this mod's changes

mcp-dev is a skill published in the GitHub repository xiaolai/vmark (878 stars, last pushed yesterday), licensed ISC. It adds 65 tokens to every session and 627 once invoked, about $0.0003 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.

Building agents

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens

vmark: Skill for Claude Code