mcp-server

mcp-server is a command for Claude Code from Flagler-County-BoCC/mcp-forge. It costs 0 tokens per session (6,963 once invoked), scanned B, original, MIT.

A project structure and implementation guide for an MCP server, a service that exposes tools for AI agents. It defines the process entry point, server factory, tool modules, HTTP client, configuration, and error handling.

In plain words
What is it for?
Use it when rewriting or structuring an MCP server with TypeScript, including tool registration, environment configuration, service wiring, and normalized errors.
Why use it?
It helps keep an MCP server organized, testable, and separated into clear responsibilities as more tools are added.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/flagler-county-bocc/mcp-forge/mcp-server
Clone the repo
git clone --depth 1 https://github.com/Flagler-County-BoCC/mcp-forge

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.

agentmods badge for mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/commands/flagler-county-bocc/mcp-forge/mcp-server.svg)](https://agentmods.dev/commands/flagler-county-bocc/mcp-forge/mcp-server)
Your own site
<a href="https://agentmods.dev/commands/flagler-county-bocc/mcp-forge/mcp-server"><img src="https://agentmods.dev/badge/commands/flagler-county-bocc/mcp-forge/mcp-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,963 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00000 $0.06963
Opus 5 $0.00000 $0.03481
Sonnet 5 $0.00000 $0.01393
Haiku 4.5 $0.00000 $0.00696

Measured 5d ago against content hash d5ad609db3ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mcp-server scanned grade B with 2 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

// ~/.claude.json — NOT ~/.claude/settings.json (that file is for preferences, not MCP)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const client = axios.create({
.claude/commands/entrypoints/mcp-server.md · 712 lines

How it starts

The opening of the file, as written. The whole thing — 712 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Entrypoint — mcp-server

This file is consumed by Step 8 of the rewrite process. Apply when AUDIT_MANIFEST.projectType === "mcp-server".

Architecture Overview

src/stdio.ts          ← process entry; connects StdioServerTransport; never imported by tests
src/server.ts         ← McpServer factory; registers all tools; importable with no side effects
src/tools/<module>/   ← one folder per logical tool group (module)
src/lib/
  container.ts        ← wires HTTP client → services; exports service instances
  http-client.ts      ← axios/got client with auth interceptors + error normalization
src/config/           ← zod-validated env (from Step 2)
src/errors/           ← AppError hierarchy (from Step 4)

src/server.ts — McpServer Factory

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { config } from './config/index.js';
import { register<Module>Tools } from './tools/<module>/<module>.tool.js';
// one import per module in AUDIT_MANIFEST.mcpTools[*].module (deduplicated)

export function createServer(): McpServer {
  const server = new McpServer({
    name: config.app?.name ?? '<projectName>',
    version: process.env['npm_package_version'] ?? '0.0.0',
  });

  // Register tools in alphabetical module order
  register<Module>Tools(server);
  // ...

  return server;
}

server.ts must NOT call server.connect() — that is stdio.ts's job. This makes server.ts testable without side effects.


src/stdio.ts — Process Entry

import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { createServer } from './server.js';
import { logger } from './lib/logger.js';
import { config } from './config/index.js';

async function main(): Promise<void> {
  const server = createServer();
  const transport = new StdioServerTransport();

  await server.connect(transport);

  logger.info(
    {
      app: config.app?.name ?? 'mcp-server',
      env: config.env,
      profile: config.mcp?.activeProfile ?? 'default',
    },
    'MCP stdio server started',
  );
}

process.on('SIGTERM', () => {
  logger.info('SIGTERM received — shutting down');
  process.exit(0);
});

process.on('SIGINT', () => {
  logger.info('SIGINT received — shutting down');
  process.exit(0);
});

process.on('unhandledRejection', (reason) => {
  logger.fatal({ reason }, 'Unhandled promise rejection');
  process.exit(1);
});

void main().catch((err) => {
  logger.fatal({ err }, 'Failed to start MCP server');
  process.exit(1);
});

Read the full file on GitHub · 712 lines

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. 5d ago First seen · 712 lines · 0 tokens per session scan B d5ad609db3ba

Subscribe to this mod's changes

mcp-server is a command published in the GitHub repository Flagler-County-BoCC/mcp-forge (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,963 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.