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.
curl -O https://raw.githubusercontent.com/japlete/md-vision-mcp/master/.agents/skills/build-mcp-server/SKILL.mdgit clone --depth 1 https://github.com/japlete/md-vision-mcpWrote 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/japlete/md-vision-mcp/build-mcp-server)<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.
<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>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 | $0.00058 | $0.00358 |
| Opus 5.5 | $0.00023 | $0.00143 |
| Sonnet 5.5 | $0.00012 | $0.00072 |
| Haiku 4.5 | $0.00006 | $0.00036 |
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 2mo 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.
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.errorfor logs. - The host starts the process and owns stdin/stdout; no listening port.
bininpackage.jsonpoints at./dist/server.js; runnpm run buildbefore 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.
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.
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.
- 2mo ago First seen · 52 lines · 58 tokens per session scan A 7c43091af1fd
build-mcp-server is a skill published in the GitHub repository japlete/md-vision-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 358 once invoked, about $0.0002 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 2026-08-31.
build-mcp-server compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-mcp-serverjaplete/md-vision-mcp | Skill | 1 | 4mo ago | MIT | A | 58 | Claude Code, Codex |
| api-test-patternslatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 56 | Claude Code |
| llm-rate-limitinglatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 49 | Claude Code |
| jwt-securitylatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 54 | Claude Code |
| api-requestssaidsef/mcp-github-pr-issue-analyser | Skill | 6 | 2d ago | Apache-2.0 | A | 37 | Claude Code, Codex |
| mcp-transport-stdio-httplatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 103 | Claude Code |
| mcp-resource-patternslatestaiagents/agent-skills | Skill | 6 | 2d ago | MIT | A | 90 | Claude Code |