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 skills add tuguang2025/tgebrowser-mcp-server --skill tgebrowsergit clone --depth 1 https://github.com/tuguang2025/tgebrowser-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/skills/tuguang2025/tgebrowser-mcp-server/tgebrowser)<a href="https://agentmods.dev/skills/tuguang2025/tgebrowser-mcp-server/tgebrowser"><img src="https://agentmods.dev/badge/skills/tuguang2025/tgebrowser-mcp-server/tgebrowser/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.
<a href="https://agentmods.dev/skills/tuguang2025/tgebrowser-mcp-server/tgebrowser"><img src="https://agentmods.dev/badge/skills/tuguang2025/tgebrowser-mcp-server/tgebrowser.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00046 | $0.03315 |
| Opus 5.5 | $0.00018 | $0.01326 |
| Sonnet 5.5 | $0.00009 | $0.00663 |
| Haiku 4.5 | $0.00005 | $0.00331 |
Grade A, and why
tgebrowser 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TgeBrowser MCP Operations
Use MCP tools to operate TgeBrowser environments, groups, proxies, and browser automation via the mcp__tgebrowser__* tools.
When to Use This Skill
Apply when the user:
- Asks to create, update, delete, or list TgeBrowser environments
- Mentions opening or closing browsers/profiles, fingerprint, UA, or proxy
- Wants to manage groups, proxies, or check API status
- Needs browser automation (navigate, click, fill forms, screenshot, etc.)
- Refers to TgeBrowser or tgebrowser operations
Ensure TgeBrowser is running (default port 50326). The MCP server connects to the TgeBrowser Local API.
Smart Defaults & Best Practices
When creating browsers:
- Always use
{"protocol": "direct"}for proxy if user doesn't specify one - Default fingerprint OS to
"Windows"if not specified - Set
webrtc: "disabled"by default for better privacy - Use
clearCacheOnStart: truefor clean sessions
When opening browsers:
- Use
args: ["--headless"]for automation tasks unless user needs to see the browser - Let the system auto-assign port unless user specifies one
When automating:
- Always call
mcp__tgebrowser__open-browserfirst and extract thewsURL from response - Then call
mcp__tgebrowser__connect-browser-with-wswith that ws URL - After connection, you can use navigation and interaction tools
Error handling:
- If browser open fails, check if TgeBrowser app is running via
mcp__tgebrowser__check-status - If envId not found, list browsers first with
mcp__tgebrowser__get-browser-list - Before deleting cache, always close the browser first
Common Workflows
Quick Start: Create and Use a Browser
- Create:
mcp__tgebrowser__create-browserwith minimal params (name + proxy) - Open:
mcp__tgebrowser__open-browserwith returned envId - Connect:
mcp__tgebrowser__connect-browser-with-wswith ws URL from step 2 - Automate: Use navigation/interaction tools
- Close:
mcp__tgebrowser__close-browserwhen done
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/country-code.md 5.1 KB
- references/environment-management.md 3.4 KB
- references/fingerprint.md 3.5 KB
- references/group.md 180 B
- references/kernel-config.md 329 B
- references/proxy-config.md 727 B
- references/proxy.md 181 B
- references/system.md 126 B
- references/tls-cipher.md 1.6 KB
- references/ua-version.md 1.3 KB
- schema.json 3.5 KB
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 · 367 lines · 46 tokens per session scan A 3700dc76be81
tgebrowser is a skill published in the GitHub repository tuguang2025/tgebrowser-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 3,315 once invoked, about $0.0002 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.
tgebrowser compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tgebrowsertuguang2025/tgebrowser-mcp-server | Skill | 0 | 3mo ago | MIT | A | 46 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | today | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 906 | yesterday | MIT | A | 40 | Claude Code |