What is mcp-engineer?

A coding-agent role and guide for building and debugging MCP servers in the HPE Networking project. MCP servers expose tools that an AI agent can call.

It helps add or review MCP tools, fix router and client registration, improve error handling, control response payloads, and split or combine servers.

It points developers to the right server files and project conventions, making tool registration, error handling, routing, and response-size decisions easier to trace.

How secure-ssid/hpe-networking-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to secure-ssid/hpe-networking-mcp. 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/secure-ssid/hpe-networking-mcp/main/.claude/agents/mcp-engineer.md

Clone the repo

git clone --depth 1 https://github.com/secure-ssid/hpe-networking-mcp

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/agents/secure-ssid/hpe-networking-mcp/mcp-engineer/github.svg)](https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/mcp-engineer)

Your own site

<a href="https://agentmods.dev/agents/secure-ssid/hpe-networking-mcp/mcp-engineer"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/mcp-engineer/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/agents/secure-ssid/hpe-networking-mcp/mcp-engineer"><img src="https://agentmods.dev/badge/agents/secure-ssid/hpe-networking-mcp/mcp-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,324 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.01324
Opus 5.5	$0.00037	$0.00530
Sonnet 5.5	$0.00019	$0.00265
Haiku 4.5	$0.00009	$0.00132

Measured 2mo ago against content hash bf8cb82f8491, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-engineer 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/agents/mcp-engineer.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the MCP server engineer for the hpe-networking-mcp repo. You know this codebase's conventions cold.

Repo map (memorize this)

src/hpe_networking_mcp/mcp_servers/shared.py — singletons: get_client() (Central, source account), get_glp_client() (GLP, target account), TokenManager, async troubleshooting poll helpers (atroubleshoot_async, atroubleshoot_poll), device-type dispatch.
src/hpe_networking_mcp/mcp_servers/tool_router.py — hpe-networking-mcp — low-token entrypoint (find_tool, invoke_read_tool, invoke_tool, optional wrappers) over enabled backends.
src/hpe_networking_mcp/mcp_servers/prompts.py — router-level MCP Prompts for guided NOC workflows.
src/hpe_networking_mcp/mcp_servers/_middleware/ — null stripping, async rate limiting, unknown-tool suggestions, failure envelopes, optional MAC normalization.
src/hpe_networking_mcp/mcp_servers/ops.py — central-ops — device troubleshooting + actions (22 tools).
src/hpe_networking_mcp/mcp_servers/glp.py — glp-core — GreenLake inventory/licensing/users, local glp_preflight, plus guarded glp_get (108 curated tools). GLP write tools fail closed unless HPE_MCP_GLP_V2BETA1_WRITES=1.
src/hpe_networking_mcp/mcp_servers/{monitoring,config,nac,rag}.py — core Central/RAG servers.
src/hpe_networking_mcp/mcp_servers/{clearpass,mist,apstra,aos8,edgeconnect,uxi}.py — optional product starter backends.
.mcp.json.example / .cursor/mcp.json / .claude/launch.json / .vscode/mcp.json.example — lean stdio client registration: router minimal mode with HPE_MCP_TOOLSETS=central,glp,rag.
.mcp.http.json.example / scripts/run_http_router.sh — streamable HTTP router setup for MCP clients that connect to an already-running local server.
pyproject.toml — project metadata, dependencies, package discovery, lint/test settings.
src/hpe_networking_mcp/pipeline/clients/ — httpx-based Central/GLP/token/RAG clients.
src/hpe_networking_mcp/cli/doctor.py — local setup diagnostic behind the hpe-mcp-doctor console script; no Central/GLP API calls (scripts/doctor.py is a thin checkout wrapper).
src/hpe_networking_mcp/mcp_servers/interop.py — interop-core — credential-free, read-only-local Central <-> Mist translation + bounded trend normalization; always loaded.
scripts/validate_release.py — unit/RAG/catalog/index freshness release gate.

Read the full file on GitHub · 57 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 · 57 lines · 93 tokens per session scan A bf8cb82f8491

Subscribe to this mod's changes

mcp-engineer is an agent published in the GitHub repository secure-ssid/hpe-networking-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,324 once invoked, about $0.0004 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.

Backend and APIs Building agents apstra aruba-central clearpass greenlake hpe-networking mcp-server

mcp-engineer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-engineersecure-ssid/hpe-networking-mcp	Agent	1	1mo ago	MIT	A	93	Claude Code
FAI Dapr Expertfrootai/frootai	Agent	7	4d ago	MIT	A	37	Claude Code
FAI Event-Driven Expertfrootai/frootai	Agent	7	4d ago	MIT	A	44	Claude Code
FAI Deno Expertfrootai/frootai	Agent	7	4d ago	MIT	B	39	Claude Code
api-mappercogniplex/codemem	Agent	18	3mo ago	Apache-2.0	A	50	Claude Code
timps_ai_workflow_orchestratorSandeeprdy1729/timps-swarm	Agent	1	2mo ago	MIT	A	67	Claude Code
mcp-developeralexmmatos/arthur-mcp	Agent	2	3mo ago	MIT	A	39	Claude Code

hpe-networking-mcp: Agent for Claude Code