What is mcp-claude-context CLAUDE.md?

Project instructions for an MCP server that extracts, stores, searches, analyzes, and exports Claude conversations. MCP is a standard that lets software expose tools to an agent.

Use it when developing or maintaining the Claude conversation context server and its related extraction, storage, search, or export code.

It gives an agent the project context needed to work safely in the repository, including its Chrome extension, bridge server, database, and search system.

How hamzaamjad/mcp-claude-context configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hamzaamjad/mcp-claude-context. 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/hamzaamjad/mcp-claude-context/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hamzaamjad/mcp-claude-context

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/hamzaamjad/mcp-claude-context/claude-md/github.svg)](https://agentmods.dev/instructions/hamzaamjad/mcp-claude-context/claude-md)

Your own site

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

Per session 2,545 This file is loaded in full into every session.

When invoked 2,545 The same file — it is already loaded in full.

Security scan B 2 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	$0.02545	$0.02545
Opus 5.5	$0.01018	$0.01018
Sonnet 5.5	$0.00509	$0.00509
Haiku 4.5	$0.00254	$0.00254

Measured 2mo ago against content hash 2549c2a3b55a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-claude-context CLAUDE.md scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 644 data/db/conversations.db

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:9222/api/status

CLAUDE.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Claude Context Server - CLAUDE.md

🎯 Project Overview

MCP (Model Context Protocol) server for extracting, storing, searching, and analyzing Claude.ai conversations with enhanced database storage, semantic search, and multiple export formats. Version 0.5.0 includes SQLite database, AI-powered search, and Docker deployment.

🏗️ Architecture

Claude.ai → Chrome Extension → Bridge Server → MCP Server → SQLite DB
                                                     ↓
                                              Search Engine
                                                     ↓
                                            Export Formats

📁 Repository Structure

mcp-claude-context/
├── src/                      # Main MCP server code
│   ├── direct_api_server.py  # Primary server (entry point)
│   ├── models/               # Database models (SQLAlchemy)
│   ├── exporters/            # Export format handlers
│   └── search/               # Search engine components
├── extension/                # Chrome extension for message extraction
│   ├── bridge_server.py      # Local HTTP server (port 9222)
│   └── content.js            # DOM extraction logic
├── deployment/               # Docker & installer scripts
├── extracted_messages/       # Local conversation storage
└── data/db/                  # SQLite database location

🚀 Quick Commands

Server Operations

# Start MCP server (main functionality)
poetry run python -m src.direct_api_server

# Start bridge server (for Chrome extension)
poetry run python extension/bridge_server.py

# Run both with Docker
cd deployment/docker && docker-compose up -d

# One-click install (Mac/Linux)
cd deployment/installer && ./install.sh

Database Operations

# Initialize database
poetry run python -c "from src.models.conversation import init_database; init_database()"

# Run migration from JSON to SQLite
poetry run python deployment/scripts/migrate_data.py

# Backup database
cp data/db/conversations.db data/db/conversations_backup_$(date +%Y%m%d).db

Read the full file on GitHub · 421 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 · 421 lines · 2,545 tokens per session scan B 2549c2a3b55a

Subscribe to this mod's changes

mcp-claude-context CLAUDE.md is an instructions file published in the GitHub repository hamzaamjad/mcp-claude-context (1 stars, last pushed 1y ago), licensed MIT. It adds 2,545 tokens to every session, about $0.0102 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context

mcp-claude-context CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-claude-context CLAUDE.mdhamzaamjad/mcp-claude-context	Instructions file	1	1y ago	MIT	B	2,545	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-claude-context: Instructions file for Claude Code