cylera-mcp-server: Instructions file for Claude Code

CLAUDE.md

cylera-mcp-server CLAUDE.md is an instructions file for Claude Code from Cylera/cylera-mcp-server. It costs 1,171 tokens per session, scanned A, original, MIT.

A project guide for an MCP server that provides read-only access to Cylera’s IoT security API. IoT means internet-connected devices; the guide covers devices, threats, risks, networks, and usage data.

In plain words
What is it for?
Developing and testing tools that find devices, inspect device details, review vulnerabilities and threats, examine risks, and retrieve subnet or usage information.
Why use it?
It gives coding agents the architecture, commands, and API behavior needed to work safely in the repository. Read-only access helps prevent changes to the security platform through this server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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 cylera-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cylera/cylera-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cylera/cylera-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,171 This file is loaded in full into every session.
When invoked 1,171 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 $0.01171 $0.01171
Opus 5.5 $0.00468 $0.00468
Sonnet 5.5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured 1mo ago against content hash 68d137b5ed60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cylera-mcp-server 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 1mo 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is an MCP (Model Context Protocol) server for Cylera that provides read-only access to the Cylera Partner API. It enables LLMs to access device inventory, threat information, risk data, and utilization metrics from Cylera's IoT security platform.

Architecture

The codebase has a simple three-layer architecture:

  1. cylera_client.py: REST API client for the Cylera Partner API

    • CyleraClient: Handles authentication (token-based with auto-refresh) and HTTP requests
    • Helper classes (Inventory, Utilization, Network, Risk, Threat): Organize API endpoints by domain
    • All API methods return Dict[str, Any] containing the raw JSON response from Cylera
  2. server.py: MCP server implementation using FastMCP

    • Exposes 13 MCP tools that wrap the Cylera API client: get_device, get_procedures, get_device_attributes, get_risk_mitigations, get_subnets, get_vulnerabilities, search_for_devices, search_excluded_devices, get_threats, get_organization, get_available_organizations, switch_organization, reset_organization
    • Formats API responses into human-readable strings or structured dictionaries
    • Tool functions are decorated with @mcp.tool() and called by LLM clients
  3. Test files:

    • test_mcp_server.py: Component tests that verify the MCP server using a test client
    • Note: cylera_client.py was moved to a separate shared package; its tests live there

Development Commands

Running Tests

All tests depend on the demo environment. Configure .env file with:

TEST_CYLERA_BASE_URL="https://partner.demo.cylera.com"
CYLERA_BASE_URL="https://partner.demo.cylera.com/"

Run all tests:

uv run pytest -v

Run tests with verbose output:

uv run pytest -v -s

Run all tests including Docker smoke test:

./test.sh

Run all tests with Doppler secrets management:

./test.sh --use-doppler

Read the full file on GitHub · 152 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. 1mo ago Changed · +27 tokens per session 68d137b5ed60
  2. 1mo ago First seen · 152 lines · 1,144 tokens per session scan A d172aa22a31c

Subscribe to this mod's changes

cylera-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Cylera/cylera-mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 1,171 tokens to every session, about $0.0047 per session on Opus 5.5. 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