agentmods.dev

mcp-server-starter: Instructions file for Claude Code

CLAUDE.md

mcp-server-starter CLAUDE.md is an instructions file for Claude Code from Axis-Data-Labs/mcp-server-starter. It costs 185 tokens per session, scanned A, original, MIT.

A project guide for building an MCP server, a program that exposes tools for an AI agent, with local and web connection methods.

In plain words
What is it for?
Use it to add tool groups, register new tools, run the server locally, or start its HTTP version with optional bearer-token authentication.
Why use it?
It explains where server code belongs and how one tool definition can support both connection methods.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Axis-Data-Labs/mcp-server-starter's own configuration. It tells Claude Code how to work on mcp-server-starter 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 mcp-server-starter configures →

not rated 0repo 4mo ago A scan 185 tokens original MIT
View source ↗ Axis-Data-Labs/mcp-server-starter
Reuse

Borrowing it

Nothing to install: this file belongs to Axis-Data-Labs/mcp-server-starter. 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/Axis-Data-Labs/mcp-server-starter/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Axis-Data-Labs/mcp-server-starter

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-starter CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/axis-data-labs/mcp-server-starter/claude-md/github.svg)](https://agentmods.dev/instructions/axis-data-labs/mcp-server-starter/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/axis-data-labs/mcp-server-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/axis-data-labs/mcp-server-starter/claude-md/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 mcp-server-starter CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/axis-data-labs/mcp-server-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/axis-data-labs/mcp-server-starter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 This file is loaded in full into every session.
When invoked 185 The same file — it is already loaded in full.
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 $0.00185 $0.00185
Opus 5.5 $0.00074 $0.00074
Sonnet 5.5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 2mo ago against content hash 43c206fe798e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server-starter CLAUDE.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 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.

CLAUDE.md · 17 lines

What it actually says

MCP Server Starter

A minimal Model Context Protocol server with two transports over one definition.

Layout

  • src/index.ts chooses the transport: stdio when PORT is unset, streamable HTTP when it is set.
  • src/server.ts builds the McpServer and registers tool groups.
  • src/tools/ holds tools, one file per domain, each exporting a register…Tools(server) function.
  • src/http.ts serves the HTTP transport with optional bearer-token auth (MCP_AUTH_TOKEN).

Add a tool

Create src/tools/<name>.ts, export register<Name>Tools(server), and call it from src/server.ts. Register with server.tool(name, description, zodSchema, handler).

Run

  • Local (stdio): npm run dev
  • HTTP: PORT=3000 npm start
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. 2mo ago First seen · 17 lines · 185 tokens per session scan A 43c206fe798e

Subscribe to this mod's changes

mcp-server-starter CLAUDE.md is an instructions file published in the GitHub repository Axis-Data-Labs/mcp-server-starter (0 stars, last pushed 4mo ago), licensed MIT. It adds 185 tokens to every session, about $0.0007 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.

Building agentsclaudemcpmcp-servermodel-context-protocolstartertemplate
Related

mcp-server-starter CLAUDE.md compared with instructions from other repositories

mcp-server-starter CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-server-starter CLAUDE.mdAxis-Data-Labs/mcp-server-starterInstructions file04mo agoMITA185Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot