mcp-context-manager: Instructions file for Claude Code

CLAUDE.md

mcp-context-manager CLAUDE.md is an instructions file for Claude Code from SanDiegoAIStudio/mcp-context-manager. It costs 1,273 tokens per session, scanned B, original, MIT.

Project instructions for MCP Context Manager, a command-line tool that discovers MCP servers and prepares them for on-demand use. MCP servers are programs that give an AI assistant access to external tools or data.

In plain words
What is it for?
Installing, discovering, optimizing, monitoring, and checking MCP usage on macOS or Linux with the project’s shell and Python commands.
Why use it?
Using many MCP servers can take up much of the assistant’s available context, leaving less room for the actual task.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

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

Reuse

Borrowing it

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

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-context-manager CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sandiegoaistudio/mcp-context-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/sandiegoaistudio/mcp-context-manager/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,273 This file is loaded in full into every session.
When invoked 1,273 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01273 $0.01273
Opus 5 $0.00636 $0.00636
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00127 $0.00127

Measured 10d ago against content hash 18147ba7ad36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

mcp-context-manager CLAUDE.md scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json | grep mcp
CLAUDE.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Context Manager (MCM) - Claude Code Project Guide

Project Location: ~/Developer/tools/mcm-context-manager Type: CLI tool for MCP optimization and context management Last Updated: 2025-11-20


Quick Start

# Install
./install.sh

# Discover and optimize MCPs
mcm discover
mcm optimize
mcm status

What MCM Does

Problem: MCP servers consume 5-15% of context window each, making it impossible to use many MCPs simultaneously.

Solution: MCM converts MCPs to optimized formats (CLI tools, scripts, skills) and loads them on-demand, saving 90-95% of context.

Results:

  • 90% context savings (26,700 → 2,800 tokens)
  • 4x more productive (30-40 tasks vs 8-10)
  • Add unlimited MCPs
  • Lower costs
  • Zero maintenance after setup

Technology Stack

  • Language: Bash scripts + Python utilities
  • No Dependencies: Pure shell scripting
  • Platform: macOS/Linux

Project Structure

mcm-context-manager/
├── src/                 # Source scripts
│   ├── discover.sh     # MCP discovery
│   ├── optimize.sh     # Optimization engine
│   └── monitor.sh      # Runtime monitoring
│
├── examples/            # Usage examples
├── docs/                # Documentation
├── install.sh           # Installation script
├── README.md            # Comprehensive guide (12KB)
└── REPO_DESCRIPTION.md  # Project description

Installation

# Clone or ensure in ~/Developer/tools/mcm-context-manager
cd ~/Developer/tools/mcm-context-manager

# Run installer
./install.sh

# Verify
mcm --version

Common Commands

# Discovery
mcm discover             # Find all MCPs
mcm discover --format [cli|script|skill]  # With format preference

# Optimization
mcm optimize             # Optimize all MCPs
mcm optimize --dry-run   # Preview changes

# Monitoring
mcm status               # Show current state
mcm stats                # Usage statistics

# Management
mcm enable [mcp-name]    # Enable MCP
mcm disable [mcp-name]   # Disable MCP
mcm list                 # List all MCPs

Read the full file on GitHub · 237 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. 10d ago First seen · 237 lines · 1,273 tokens per session scan B 18147ba7ad36

Subscribe to this mod's changes

mcp-context-manager CLAUDE.md is an instructions file published in the GitHub repository SanDiegoAIStudio/mcp-context-manager (2 stars, last pushed 25d ago), licensed MIT. It adds 1,273 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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 · 5,153 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

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

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