junos-mcp-server: Instructions file for Claude Code

CLAUDE.md

junos-mcp-server CLAUDE.md is an instructions file for Claude Code from workfloworchestrator/junos-mcp-server. It costs 426 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a read-only MCP server that troubleshoots Junos network devices. It allows only show commands and blocks commands that could save, append, copy, or load configuration.

In plain words
What is it for?
Use it when developing or testing the Junos server, validating network commands, discovering configured targets, or running read-only device troubleshooting.
Why use it?
It documents the safety boundary, project layout, device discovery, development mode, and tests so changes do not accidentally add write access.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/workfloworchestrator/junos-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/workfloworchestrator/junos-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 426 This file is loaded in full into every session.
When invoked 426 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 $0.00426 $0.00426
Opus 5.5 $0.00170 $0.00170
Sonnet 5.5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured 2mo ago against content hash e58a4601705a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

junos-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 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.

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 · 35 lines

What it actually says

CLAUDE.md

Read-only JUNOS troubleshooting MCP server.

Invariant (do not break)

Read-only only. NEVER add a configuration/write tool. Every device command goes through validate_show_command(), which allows only show commands and blocks | save / | append / | tee / | load.

Layout

  • src/junos_mcp_server/server.py — the whole server: Settings (pydantic-settings BaseSettings, env vars via validation_alias) + settings(), fetch_targets() (cached), the ShowCommand pydantic model + validate_show_command(), run_show() (PyEZ), and FastMCP tools list_devices / run_show_command.
  • tests/test_server.py — parametrized unit tests for the command validator, target parsing, and tool dispatch. (Settings is plain pydantic — not retested.)

Targets source

GET {ORCHESTRATOR_URL}/api/surf/subscriptions/gnmi/targets (Basic Auth). The address field is fqdn:32767 (gNMI port) — we use the FQDN only and connect NETCONF on JUNOS_SSH_PORT (830).

Dev mode: JUNOS_DEV_MODE=1 + JUNOS_DEV_TARGETS (JSON list of node hostnames) makes fetch_targets() return {node: node} and skip the orchestrator. A model_validator enforces the mode rules: dev needs non-empty JUNOS_DEV_TARGETS; prod needs ORCHESTRATOR_URL + GNMIC_HTTP_BASIC_*. SSH creds required in both.

Test

uv run --extra dev pytest -v

Style

Prefer comprehensions / itertools / next(..., None) over imperative loops, break, continue. Use @pytest.mark.parametrize for data-varying tests.

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. 2mo ago First seen · 35 lines · 426 tokens per session scan A e58a4601705a

Subscribe to this mod's changes

junos-mcp-server CLAUDE.md is an instructions file published in the GitHub repository workfloworchestrator/junos-mcp-server (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 426 tokens to every session, about $0.0017 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

junos-mcp-server CLAUDE.md compared with instructions from other repositories

junos-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
junos-mcp-server CLAUDE.mdworkfloworchestrator/junos-mcp-serverInstructions file023d agoApache-2.0A426Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot