mcp-server-claude: Instructions file for Claude Code

CLAUDE.md

mcp-server-claude CLAUDE.md is an instructions file for Claude Code from zcc-cddg-mx/mcp-server-claude. It costs 810 tokens per session, scanned B, original, Apache-2.0.

Project instructions for an MCP memory server used with Claude Code. It stores session information locally with a database and searches past context using text embeddings, which are numeric representations of meaning.

In plain words
What is it for?
Use it to install dependencies, understand the server's FastMCP, ChromaDB, SQLite, and sentence-transformers stack, and configure the server to run through standard input and output.
Why use it?
It provides a shared reference for the project's structure, technology choices, commands, and setup, including memory that can persist between sessions.

Instructions file for Claude Code

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

This is zcc-cddg-mx/mcp-server-claude's own configuration. It tells Claude Code how to work on mcp-server-claude 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-server-claude configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/idavid/dev/.

Reuse

Borrowing it

Nothing to install: this file belongs to zcc-cddg-mx/mcp-server-claude. 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/zcc-cddg-mx/mcp-server-claude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zcc-cddg-mx/mcp-server-claude

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-server-claude CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zcc-cddg-mx/mcp-server-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/zcc-cddg-mx/mcp-server-claude/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 810 This file is loaded in full into every session.
When invoked 810 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 $0.00810 $0.00810
Opus 5 $0.00405 $0.00405
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 9d ago against content hash 572d6de93f6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

mcp-server-claude 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 9d 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.

├── mcp_config.example.json ← snippet para ~/.claude/settings.json
CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mcp-server-claude

MCP Memory Server para Claude Code. Proporciona contexto persistente entre sesiones via RAG (ChromaDB + sentence-transformers). Diseñado para el entorno Zurich Insurance GenAI Platform (LiteLLM proxy UAT, WSL2 Ubuntu 24).

Stack

  • Framework MCP: FastMCP (Python) — genera JSON schemas automáticamente desde type hints Pydantic v2
  • Vector store: ChromaDB (local, sin servidor)
  • Relational store: SQLite (metadatos de sesiones)
  • Embeddings: sentence-transformers all-MiniLM-L6-v2 (local, ~80MB, ~10ms/embedding)
  • Transporte: STDIO — corre como proceso hijo de Claude Code

Estructura

mcp-server-claude/
├── CLAUDE.md
├── README.md
├── requirements.txt
├── .env.example
├── mcp_config.example.json     ← snippet para ~/.claude/settings.json
├── docs/
│   ├── ANALYSIS.md             ← arquitectura, decisiones, investigación
│   └── projects.md             ← inventario de repos gestionados
└── src/
    ├── server.py               ← punto de entrada FastMCP
    ├── memory_store.py         ← abstracción ChromaDB + SQLite
    └── embeddings.py           ← wrapper sentence-transformers

Comandos

# Instalar dependencias
pip install -r requirements.txt

# Correr el server en modo debug (stderr visible)
python src/server.py

# Registrar en Claude Code (copiar snippet de mcp_config.example.json a ~/.claude/settings.json)

Regla crítica de implementación

Nunca escribir a stdout. El transporte STDIO reserva stdout exclusivamente para JSON-RPC 2.0. Todo logging debe ir a sys.stderr:

import sys, logging
logging.basicConfig(stream=sys.stderr, level=logging.INFO)
# NUNCA: print(...)  ← corrompe el protocolo

Variables de entorno

Ver .env.example. Las variables relevantes:

Variable Descripción
MEMORY_DB_PATH Ruta al directorio de datos ChromaDB + SQLite (fuera del repo)
EMBEDDING_MODEL Modelo sentence-transformers a usar
LOG_LEVEL Nivel de logging (INFO por defecto)

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 810 tokens per session scan B 572d6de93f6d

Subscribe to this mod's changes

mcp-server-claude CLAUDE.md is an instructions file published in the GitHub repository zcc-cddg-mx/mcp-server-claude (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 810 tokens to every session, about $0.0040 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens