md-vision-mcp: Skill for Claude Code

.agents/skills/build-mcp-server/SKILL.md

build-mcp-server is a skill for Claude Code, Codex from japlete/md-vision-mcp. It costs 58 tokens per session (358 once invoked), scanned A, original, MIT.

A set of instructions for developing the md-vision Model Context Protocol server, a local program that gives AI agents tools for reading Markdown files with embedded images and indexing their headings. It covers the TypeScript server, tool registration, transport, schemas, and testing.

In plain words
What is it for?
Use it to add or change md-vision tools, connect the server through standard input/output, validate it with the MCP Inspector, or debug tool schemas and image-enabled responses.
Why use it?
It keeps changes consistent with this repository’s structure and rules, including its local standard input/output connection and safety restrictions. It also helps catch invalid tool schemas and multimodal response problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is japlete/md-vision-mcp's own configuration. It tells Claude Code and Codex how to work on md-vision-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything md-vision-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to japlete/md-vision-mcp. 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/japlete/md-vision-mcp/master/.agents/skills/build-mcp-server/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/japlete/md-vision-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for build-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/japlete/md-vision-mcp/build-mcp-server/github.svg)](https://agentmods.dev/skills/japlete/md-vision-mcp/build-mcp-server)
Your own site
<a href="https://agentmods.dev/skills/japlete/md-vision-mcp/build-mcp-server"><img src="https://agentmods.dev/badge/skills/japlete/md-vision-mcp/build-mcp-server/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.

agentmods 80×15 button for build-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/japlete/md-vision-mcp/build-mcp-server"><img src="https://agentmods.dev/badge/skills/japlete/md-vision-mcp/build-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00358
Opus 5 $0.00029 $0.00179
Sonnet 5 $0.00012 $0.00072
Haiku 4.5 $0.00006 $0.00036

Measured 10d ago against content hash 7c43091af1fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

build-mcp-server 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 10d 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.

.agents/skills/build-mcp-server/SKILL.md · 52 lines

What it actually says

MCP server quickstart

Repo level instructions have precedence over this generic skill.

Server skeleton

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new McpServer({
  name: "md-vision",
  version: "0.1.0",
});

// server.tool(...) or server.registerTool(...) — match whichever API the installed SDK exposes

async function main(): Promise<void> {
  const transport = new StdioServerTransport();
  await server.connect(transport);
}

main().catch((err) => {
  console.error(err);
  process.exit(1);
});

stdio rules:

  • Never write to stdout except MCP protocol messages. Use console.error for logs.
  • The host starts the process and owns stdin/stdout; no listening port.
  • bin in package.json points at ./dist/server.js; run npm run build before testing.

Tool design

→ See references/tool-design.md for description and schema guidance.


Security

Restrict paths and domains via CLI flags. Block filesystem and network access by default if no flags are provided. MCP Roots is deprecated in the next MCP standard — do not use it here.

Files

What ships with it

1 file 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.

  1. 10d ago First seen · 52 lines · 58 tokens per session scan A 7c43091af1fd

Subscribe to this mod's changes

build-mcp-server is a skill published in the GitHub repository japlete/md-vision-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 358 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

swarm-build

Build SwarmAI backend binary (PyInstaller), verify capabilities, deploy to daemon, and restart. Replaces ./prod.sh build with per-stage visibility. TRIGGER: "build", "build backend", "swarm build", "deploy binary". NOT FOR: sswarm-release use cases.

xg-gh-25/SwarmAI · 66 tokens

api-security

Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.

xAmirHamza77/ReverseOps-Skill · 36 tokens

protocol-reverse

Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.

xAmirHamza77/ReverseOps-Skill · 30 tokens

building-mcp-servers

Use this skill whenever the user wants to design, build, harden, review, or debug an MCP (Model Context Protocol) server — including "build me an MCP server for X", connecting an AI agent/Claude to a database or API, adding tools/resources to an existing MCP server, reviewing a contributor PR against an MCP server, or…

cyberreinxy/mcp-server-skill · 160 tokens

implementing-mcp-resources

Implement new MCP resources and resource templates in the deno-mcp-template project. Provides the exact file structure, type signatures, registration steps, and patterns for static resources, KV-backed resources, resource templates with URI patterns, and subscription-based updates. Use when adding a new resource…

phughesmcr/deno-mcp-template · 76 tokens

api-test-patterns

Write comprehensive API tests for REST and GraphQL endpoints. Use this skill when testing APIs, writing contract tests, or validating integrations. Activate when: api testing, REST test, GraphQL test, endpoint testing, integration test, postman, contract testing.

latestaiagents/agent-skills · 56 tokens