Localmcp — AI skill for Claude Code
A local, scoped, read-first browser for AI agents (MCP + CLI).
How to install Localmcp
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open NETWORK101/localmcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Localmcp does
A local, scoped, read-first browser for AI agents (MCP + CLI). The page itself, not a summary.
Alternatives in AI
- UltraCode Shim — Give Claude Code's ultracode mode to ANY model you already pay for 422 ★
- Yt Transcriber — CLI app- Give it a YouTube URL and you get a transcription with possible speaker identification and optional s 337 ★
- Engrim — The Universal Cross-Model Episodic Memory Standard 219 ★
README
localmcp
**A local, read-optimized browser for AI agents.** Your agent reads any page — including the ones you're signed in to — as focused, token-budgeted markdown. Runs a real Chromium on your machine. No cloud relay, no API key, no account.
claude mcp add localmcp -- npx -y @network101/localmcp # Claude Code
npx @network101/localmcp init # everything else: prints config for your clients
[](https://www.npmjs.com/package/localmcp) · MIT · Node ≥ 20 · [Website](https://localmcp.pages.dev)
Why
| Option | Problem for agents |
|---|---|
| Built-in web fetch (e.g. Claude Code's WebFetch) | No cookies, no JavaScript, refuses localhost, and large pages come back as a small-model summary rather than the page. |
| Cloud scrapers (Firecrawl, Jina, Browserbase) | Your Stripe dashboard, internal wiki, and localhost:3000 go through someone else's servers — or can't be reached at all. |
| Full automation MCPs (e.g. Playwright MCP) | Great for driving a browser. For reading, one page snapshot is 13k–87k tokens of accessibility tree (measured). |
| CLI browser tools | Need a shell. Claude Desktop and other sandboxed clients don't have one. |
localmcp is the reading-first option: the page itself — no summarizer in the middle — focused and under a token budget, read by a browser on your machine. Five MCP tools, or three shell commands. See the [benchmark](benchmarks/results.md).
What's new in 0.2
- Real authenticated browsing.
npx @network101/localmcp loginopens a visible browser on a private profile. Sign in once; the agent reuses the session. Or attach to your own Chrome over CDP. - Focus + budget.
browse({ url, focus: "rate limits", maxTokens: 1500 })ranks sections by relevance and returns only what fits — and tells the agent which sections it left out. - Structured extraction with MCP sampling.
extractreturns JSON-LD,
Related Skills
Projectmind
AI-driven architecture browser: MCP server + desktop app. Claude Code, Codex & other AI agents explain your co
Elsm MCP
Local MCP bridge for Easy Local Storage Manager: lets any AI agent (Claude Code, Cursor, Codex, Gemini CLI, ..
MCP Warden
Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and datab
Agentic Access Control
Read-only, local-first dashboard showing what your AI agents (Claude Code, Gemini CLI, MCP servers) are actual
Browser4agent
Expose browser tab reading, browser control, and page tool execution to user-configured AI agents through a lo
Yx Bridge
Browser extension + local MCP server: 250+ tools so an AI agent can read and control your open tabs (Yandex Br
Related Agents
Plugin Dev
Scoped guide for work on the herdr-plugin-pipeline plugin itself — the hpipe CLI, the supervisor, the phase ma
Cortex Maintainer
Develops and fixes Córtex itself (3D web in src/, Python analyzer in analyzer/cortex_graph/, CLI, MCP server,
Ideal Customer
You are exactly the person this page is for. First, work out who that is from the page itself (the audience it