What is mcp CLAUDE.md?

A repository guide for Claude Code, an AI coding assistant, covering the project’s purpose, commands, architecture, and coding conventions. The project teaches MCP, a standard way for AI applications to call external tools.

Use it when working on this MCP teaching repository, especially before running tests, editing examples, or changing behavior that the comments explain.

It gives the coding assistant the context needed to make appropriate changes. It also treats explanatory comments as part of the teaching material.

How nikhilpatil79/mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nikhilpatil79/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.

Copy the file

curl -O https://raw.githubusercontent.com/nikhilpatil79/mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nikhilpatil79/mcp

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/nikhilpatil79/mcp/claude-md.svg)](https://agentmods.dev/instructions/nikhilpatil79/mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nikhilpatil79/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nikhilpatil79/mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,200 This file is loaded in full into every session.

When invoked 1,200 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	$0.01200	$0.01200
Opus 5	$0.00600	$0.00600
Sonnet 5	$0.00240	$0.00240
Haiku 4.5	$0.00120	$0.00120

Measured 7d ago against content hash 9e054a543aa1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp 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 7d 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this repository is

A teaching workspace for the Model Context Protocol, in two halves:

src/notes_server/ — a reference MCP server on the official Python SDK (mcp 1.x, FastMCP). Every primitive exactly once, heavily commented.
src/mcp_lab_ui/ — a local Starlette dashboard that connects to the servers in .mcp.json as a real MCP client and logs the JSON-RPC frames in transit.

The comments are the product. This is the single most important thing to know before editing. In a normal repository a stale comment is untidy; here it is a bug, because people read this code to learn what MCP is. If you change behaviour, the surrounding prose must change with it — and if you cannot explain a change in the file's existing voice, that is a signal the change is wrong.

Commands

uv sync --group dev          # install, including dev tools
uv run pytest -q             # the test suite (no Docker, no network)
uv run ruff check .          # lint -- must pass, CI gates on it
uv run ruff format --diff .  # advisory only, NOT a gate (see below)

docker compose up -d --wait                 # local Postgres
uv run mcp-lab-ui                           # the dashboard on :8765
uv run python scripts/drive_servers.py      # smoke-test every server in .mcp.json
uv run mcp dev src/notes_server/server.py   # the MCP Inspector

ruff format is deliberately advisory. Some layout in the teaching files is hand-tuned for readability and the formatter disagrees. Do not "fix" the codebase to satisfy it, and do not promote it to a gate.

Architecture notes

store.py holds no MCP code, on purpose. The separation is itself a lesson: an MCP server is a thin protocol wrapper over capabilities an application already has. Keep domain logic out of server.py.
hub.py::_tap inserts a pair of anyio memory streams between stdio_client and ClientSession and pumps messages across, logging each one. This is why the dashboard shows real frames rather than a reconstruction. Do not replace it with a wrapper that synthesises frames.
pipeline.py parses .github/workflows/*.yml at request time rather than restating what they contain, so the page cannot drift from the YAML. Preserve that property.
Tests drive the server as a client via the SDK's in-memory transport (create_connected_server_and_client_session), exercising the real protocol instead of calling the decorated functions directly. New server tests should follow that pattern.

Read the full file on GitHub · 101 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.

7d ago First seen · 101 lines · 1,200 tokens per session scan A 9e054a543aa1

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository nikhilpatil79/mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 1,200 tokens to every session, about $0.0060 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.

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

mcp: Instructions file for Claude Code