mcp-uplift: Instructions file for Claude Code

CLAUDE.md

mcp-uplift CLAUDE.md is an instructions file for Claude Code from MohibShaikh/mcp-uplift. It costs 1,720 tokens per session, scanned A, original, MIT.

Development instructions for mcp-uplift, a bridge that lets a trusted older MCP server use the newer stateless protocol. It keeps one older server session running while presenting it as a stateless server.

In plain words
What is it for?
Use it when implementing or reviewing mcp-uplift, especially its protocol translation. It also sets conventions for keeping complex code simple and explaining why comments exist.
Why use it?
It helps developers translate protocol messages without guessing about method names or data fields. The instructions require checking the official protocol sources before writing protocol-facing code.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to MohibShaikh/mcp-uplift. 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/MohibShaikh/mcp-uplift/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MohibShaikh/mcp-uplift

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-uplift CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mohibshaikh/mcp-uplift/claude-md.svg)](https://agentmods.dev/instructions/mohibshaikh/mcp-uplift/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mohibshaikh/mcp-uplift/claude-md"><img src="https://agentmods.dev/badge/instructions/mohibshaikh/mcp-uplift/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,720 This file is loaded in full into every session.
When invoked 1,720 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 $0.01720 $0.01720
Opus 5 $0.00860 $0.00860
Sonnet 5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured 7d ago against content hash 1b02080f1640, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-uplift 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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-uplift

A bridge that runs a trusted legacy MCP stdio server behind the stateless 2026-07-28 protocol. One legacy session is kept warm and presented as a stateless modern server.

Working conventions

Simple implementations for complex concepts

The problems here are intricate; the code should not be. Prefer a plain data structure and a short function over a framework or a clever abstraction. A reader should be able to follow the protocol translation without first learning an internal vocabulary. If a concept is genuinely hard, spend the words in a comment explaining why, not in machinery.

No assumptions, only verified truths

Never write protocol behavior from memory or inference. Before implementing anything spec-facing, fetch the actual source and work from what it says:

  • Spec prose: docs/specification/2026-07-28/ in modelcontextprotocol/modelcontextprotocol (reachable via gh api).
  • Schema and canonical payloads: schema/2026-07-28/, including the examples/ directory, which holds real request/response JSON.

Quote exact method and field names from those sources. If a detail cannot be verified, say so and stop rather than guessing at a wire format. Blog posts and summaries are leads, not authority.

Comments explain why, not what

Existing comments in src/ state the reason a thing is done the way it is (usually a protocol constraint or a failure that forced it). Match that. Do not narrate what the next line already says.

Commit messages

Conventional-commit subject, then a body that leads with the problem and only then the change, wrapped near 72 columns. Release commits are the bare version string (0.1.2), which is what npm version writes. No Co-Authored-By trailers.

Honest limitations

The README's "Known limitations" section is load-bearing. When a limitation narrows, rewrite it to match reality; do not delete it and do not overstate what was fixed.

Numbers must come from a run that happened

The README's "Verified against real servers" table states counts. Every one of them must trace to a sweep that actually completed, and it separates three numbers that are easy to blur into one:

Read the full file on GitHub · 151 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. 7d ago First seen · 151 lines · 1,720 tokens per session scan A 1b02080f1640

Subscribe to this mod's changes

mcp-uplift CLAUDE.md is an instructions file published in the GitHub repository MohibShaikh/mcp-uplift (2 stars, last pushed 23d ago), licensed MIT. It adds 1,720 tokens to every session, about $0.0086 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

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 · 5,153 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

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

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

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

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