What is localhost-mcp CLAUDE.md?

Project instructions for localhost-mcp, an MCP server that inspects development servers running on a computer. MCP is a way for an AI agent to call tools provided by another program.

Use it to list local development servers, inspect ports and process details, find likely leftover servers, and check or resolve port conflicts.

It helps the agent find running local servers, inspect their processes, spot unused servers, and detect port conflicts. It also documents safety limits around stopping processes.

How HasanJahidul/localhost-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to HasanJahidul/localhost-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/HasanJahidul/localhost-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/HasanJahidul/localhost-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/instructions/hasanjahidul/localhost-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hasanjahidul/localhost-mcp/claude-md)

Your own site

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

Per session 1,045 This file is loaded in full into every session.

When invoked 1,045 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.

Model	Per session	Once invoked
Fable 5.1	$0.01045	$0.01045
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 2mo ago against content hash ab4b7f012a7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localhost-mcp 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

localhost-mcp — Project Context

MCP server that inspects local dev servers via lsof + ps. macOS/Linux first, Windows partial. Sibling project to terminal-history-mcp (same author, same TS+npm pattern).

Status

Version: 0.1.0 scaffold (this commit)
Working dir: /Users/jahidulhasan/Documents/research/mcp-servers/localhost-mcp
Wire: claude mcp add --scope user localhost -- localhost-mcp (after npm link)

Architecture

src/
├── cli.ts          Bin entry. Subcommands: (none → server) | server | list | zombies | --version | --help.
├── index.ts        MCP stdio server. Registers 5 tools.
├── scanner.ts      Port scan via lsof (unix) / netstat (win). Returns {port, pid, process, user}.
├── process.ts      ps -o lookup for cmdline/uptime/cpu/rss. cwd via /proc (linux) or lsof (mac). Framework detect from cmdline + package.json sniff.
├── dev-servers.ts  High-level: listDevServers, portInfo, findZombies, portConflict. Whitelist filter.
├── killer.ts       SIGTERM → 5s wait → SIGKILL escalation. Refuses pid<1000. Dry-run unless confirm=true.
└── types.ts        DevServer, ZombieCandidate, Platform.

MCP Tools

Tool	Purpose
`list_dev_servers`	All dev servers w/ port/pid/framework/cwd/uptime/mem/cpu
`port_info`	Single port lookup
`kill_server`	Kill by pid OR port. Dry-run unless `confirm:true`. SIGKILL via `force:true`
`find_zombies`	Heuristic: uptime>24h + cpu<1% + mem>200MB → 2/3 = zombie
`port_conflict`	Blocking server + 5 free alternatives nearby

Safety

kill_server defaults to dry-run.
Refuses PIDs < 1000 (system).
Whitelist of dev process names in src/dev-servers.ts DEV_PROCESS_WHITELIST.
Cmdline regex fallback for runners not in whitelist.

Tech Decisions

TS + Node 18+ — match terminal-history-mcp; ESM ("type": "module").
No SDK for lsof — shell out to lsof directly via execFile. No deps.
No DB — stateless, query live each call. Fast enough; port scan ~50ms.
Stdio MCP transport — local tool, no HTTP needed.
Zod for kill_server args only — other tools have trivial schemas.

Read the full file on GitHub · 96 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 · 96 lines · 1,045 tokens per session scan A ab4b7f012a7b

Subscribe to this mod's changes

localhost-mcp CLAUDE.md is an instructions file published in the GitHub repository HasanJahidul/localhost-mcp (4 stars, last pushed 5mo ago), licensed MIT. It adds 1,045 tokens to every session, about $0.0042 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.

claude dev-server localhost lsof mcp model-context-protocol

localhost-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
localhost-mcp CLAUDE.mdHasanJahidul/localhost-mcp	Instructions file	4	5mo ago	MIT	A	1,045	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

localhost-mcp: Instructions file for Claude Code