mcp-testbed: Instructions file for Claude Code

CLAUDE.md

mcp-testbed CLAUDE.md is an instructions file for Claude Code from anthonys1760/mcp-testbed. It costs 1,664 tokens per session, scanned A, original, MIT.

Instructions for building an MCP server, a program that gives an AI agent tools through a standard interface. This server uses MCP SDK version 2 and provides an isolated workspace, test execution, and repeatable pass-or-fail results.

In plain words
What is it for?
Use it when changing this MCP server, registering tools, defining input and output schemas, or checking deterministic test behavior.
Why use it?
It prevents common version mistakes and defines how to preserve identical results when the same code is tested more than once.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is anthonys1760/mcp-testbed's own configuration. It tells Claude Code how to work on mcp-testbed 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-testbed configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anthonys1760/mcp-testbed. 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/anthonys1760/mcp-testbed/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/anthonys1760/mcp-testbed

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-testbed CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anthonys1760/mcp-testbed/claude-md.svg)](https://agentmods.dev/instructions/anthonys1760/mcp-testbed/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anthonys1760/mcp-testbed/claude-md"><img src="https://agentmods.dev/badge/instructions/anthonys1760/mcp-testbed/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,664 This file is loaded in full into every session.
When invoked 1,664 The same file — it is already loaded in full.
Security scan A 0 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 5.1 $0.01664 $0.01664
Opus 5 $0.00832 $0.00832
Sonnet 5 $0.00333 $0.00333
Haiku 4.5 $0.00166 $0.00166

Measured 5d ago against content hash 9e4d2870d268, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-testbed 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 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.

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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in this repository.

What this is

An MCP server that gives an agent an isolated workspace, runs its tests, and returns a deterministic pass/fail verdict. Determinism is the product. Anything that makes two runs of identical code produce different output is a bug, and the end to end test asserts byte identical output across two workspaces.

Read README.md for the user facing description. This file covers what you need to change code safely.

Critical: this uses MCP SDK v2, not v1

This is the single most likely thing to get wrong, because v1 is far more common in training data.

Correct (what this repo uses):

import { McpServer } from '@modelcontextprotocol/server';
import { StdioServerTransport } from '@modelcontextprotocol/server/stdio';
import * as z from 'zod';

server.registerTool(
  'tool_name',
  {
    title: 'Human readable title',
    description: '...',
    inputSchema: z.object({ field: z.string() }),
    outputSchema: z.object({ result: z.string() }),
    annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: true },
  },
  async ({ field }) => ({
    content: [{ type: 'text', text: JSON.stringify(output) }],
    structuredContent: output,
  }),
);

Wrong (v1 API, will not work here):

  • import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
  • import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
  • server.tool(name, description, schema, handler)
  • Passing a raw Zod shape { field: z.string() } instead of z.object({ ... }). The raw shape form still exists but is deprecated.

The client package is @modelcontextprotocol/client v2, used only in tests.

If you need to check an API, read the types in node_modules/@modelcontextprotocol/server/dist/createMcpHandler-*.d.mts. The barrel file index.d.mts is a minified re-export and is not readable.

Commands

npm test                          # all tests, via tsx + node:test
npx tsx --test test/normalize.test.ts   # a single file
npm run typecheck                 # tsc --noEmit
npm run build                     # tsc, emits to dist/
npm start                         # runs the built server on stdio

Read the full file on GitHub · 126 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 · 126 lines · 1,664 tokens per session scan A 9e4d2870d268

Subscribe to this mod's changes

mcp-testbed CLAUDE.md is an instructions file published in the GitHub repository anthonys1760/mcp-testbed (0 stars, last pushed 24d ago), licensed MIT. It adds 1,664 tokens to every session, about $0.0083 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens