Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jediluke/firefox-mcp-server/claude-mdgit clone --depth 1 https://github.com/JediLuke/firefox-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/jediluke/firefox-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jediluke/firefox-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jediluke/firefox-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01553 | $0.01553 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00311 | $0.00311 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
firefox-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 189 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.
Development Commands
Running the Server
npm start- Run the MCP servernpm run dev- Run server with Node.js debugger
Testing
npm test- Run basic Firefox functionality testnpm run install-firefox- Install Firefox browser for Playwright
Example Scripts
npm run example:basic- Run basic demo scriptnpm run example:multiplayer- Run multiplayer testing demo
Active Implementation
The MCP server implementation is in index.js.
The server provides:
- Class:
FirefoxMCPServer(version 1.0.0) - 29 MCP tools for browser automation and debugging
- Multi-session support with complete isolation
- Advanced debugging capabilities (console logs, WebSocket monitoring, network activity, performance metrics)
Architecture Overview
Core Components
- MCP Server: Uses
@modelcontextprotocol/sdkfor stdio communication - Browser Engine: Playwright Firefox automation
- Session Management: Map-based storage for browser contexts and pages
- Debug Buffers: Per-tab in-memory storage for monitoring data
Key Data Structures
this.browser- Main Firefox browser instancethis.contexts- Map of contextId → BrowserContext (for session isolation)this.pages- Map of tabId → Page (for tab management)this.consoleLogs- Map of tabId → array of console log eventsthis.jsErrors- Map of tabId → array of JavaScript error eventsthis.networkActivity- Map of tabId → array of network eventsthis.wsMessages- Map of tabId → array of WebSocket messagesthis.performanceMetrics- Map of tabId → performance datathis.activeTabId- Currently active tab identifier
Session Isolation Architecture
Each session gets its own browser context with:
- Separate cookies and storage
- Independent session data
- Isolated network monitoring
- Individual debug buffers
Tool Categories
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.
- 4d ago First seen · 189 lines · 1,553 tokens per session scan A 60f5b55ed87a
firefox-mcp-server CLAUDE.md is an instructions file published in the GitHub repository JediLuke/firefox-mcp-server (30 stars, last pushed 8mo ago), licensed MIT. It adds 1,553 tokens to every session, about $0.0078 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
browser_oxide AGENTS.md
AGENTS.md instructions for yfedoseev/browser_oxide, covering browseroxide — conventions for ai coding assistants, build & test, architecture, key conventions and where to read more.