What is mcp-framework CLAUDE.md?

Repository instructions for developing mcp-framework, a TypeScript framework for building Model Context Protocol servers. They describe the project, development commands, testing, linting, formatting, and local package publishing.

Use them when building, watching, testing, linting, formatting, or locally publishing this TypeScript framework and projects that use it.

They give a coding agent the project-specific commands and conventions needed to make changes without guessing how the repository works.

How QuantGeekDev/mcp-framework configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QuantGeekDev/mcp-framework. 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/QuantGeekDev/mcp-framework/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/QuantGeekDev/mcp-framework

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/quantgeekdev/mcp-framework/claude-md/github.svg)](https://agentmods.dev/instructions/quantgeekdev/mcp-framework/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/quantgeekdev/mcp-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/quantgeekdev/mcp-framework/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/quantgeekdev/mcp-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/quantgeekdev/mcp-framework/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,151 This file is loaded in full into every session.

When invoked 2,151 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.

Model	Per session	Once invoked
Fable 5.1	$0.02151	$0.02151
Opus 5.5	$0.00860	$0.00860
Sonnet 5.5	$0.00430	$0.00430
Haiku 4.5	$0.00215	$0.00215

Measured 2mo ago against content hash f65a3ed05096, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-framework 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 · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

mcp-framework is a TypeScript framework for building Model Context Protocol (MCP) servers. It provides an opinionated architecture with automatic directory-based discovery for tools, resources, and prompts. The framework is used as a dependency in other projects (similar to Express.js) and runs from node_modules.

Development Commands

Build and Watch

npm run build          # Compile TypeScript to dist/
npm run watch          # Watch mode for development

Testing

npm test                    # Run all tests
npm run test:watch          # Run tests in watch mode
npm run test:coverage       # Run tests with coverage report

Linting and Formatting

npm run lint            # Run ESLint
npm run lint:fix        # Run ESLint with auto-fix
npm run format          # Format code with Prettier

Local Development with yalc

npm run dev:pub         # Build and publish to yalc for local testing

CLI Commands (for projects using the framework)

mcp create <project-name>           # Create new MCP server project
mcp add tool <tool-name>            # Add a new tool
mcp add prompt <prompt-name>        # Add a new prompt
mcp add resource <resource-name>    # Add a new resource
mcp validate                        # Validate tool schemas
mcp-build                          # Build project (used in build scripts)

Architecture

Core Components

MCPServer (src/core/MCPServer.ts)
- Main server class that orchestrates everything
- Handles capability detection (tools, prompts, resources)
- Manages transport configuration (stdio, SSE, HTTP stream)
- Loads and validates tools/prompts/resources on startup
- Resolves basePath from config or process.argv[1] or process.cwd()
Loaders (src/loaders/)
- ToolLoader, PromptLoader, ResourceLoader
- Automatically discover and load implementations from directories
- Look for files in <basePath>/tools, <basePath>/prompts, <basePath>/resources
- Load from compiled JS in dist/ (not from src/)

Read the full file on GitHub · 245 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.

2mo ago First seen · 245 lines · 2,151 tokens per session scan A f65a3ed05096

Subscribe to this mod's changes

mcp-framework CLAUDE.md is an instructions file published in the GitHub repository QuantGeekDev/mcp-framework (931 stars, last pushed 6mo ago), licensed MIT. It adds 2,151 tokens to every session, about $0.0086 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 2026-08-30.

LLM Languages Testing TypeScript claude genai llms mcp modelcontextprotocol

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 · 9,715 tokens

mcp-framework: Instructions file for Claude Code