LangBot is an open-source platform for connecting language models to instant-messaging services so developers can build chatbots that converse, use tools, and execute tasks. It supports bot management, knowledge bases, plugins, and multiple chat platforms, and the catalogue entries provide skills, MCP tools, and instructions for working with it.
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.
git clone --depth 1 https://github.com/langbot-app/LangBotWrote 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/mcp/langbot-app/langbot/playwright)<a href="https://agentmods.dev/mcp/langbot-app/langbot/playwright"><img src="https://agentmods.dev/badge/mcp/langbot-app/langbot/playwright/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/mcp/langbot-app/langbot/playwright"><img src="https://agentmods.dev/badge/mcp/langbot-app/langbot/playwright.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
playwright 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 1mo 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- playwright — 100% identical, 0 lines differ
- playwright — 100% identical, 1 lines differ
- playwright — 100% identical, 1 lines differ
- playwright — 100% identical, 0 lines differ
- playwright — 100% identical, 0 lines differ
- playwright — 100% identical, 0 lines differ
- playwright — 100% identical, 1 lines differ
- playwright — 100% identical, 0 lines differ
What it actually says
{
"playwright": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@playwright/mcp@latest"
],
"env": {}
}
}What else .mcp.json configures
This page is one entry in a file that holds 5. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 1mo ago First seen · 11 lines scan A 526b267b5297
playwright is an MCP server published in the GitHub repository langbot-app/LangBot (18,191 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
mintlify-docs
MCP server "mintlify-docs", hosted remotely at www.mintlify.com, as configured in nottelabs/notte.
notte-docs
MCP server "notte-docs", hosted remotely at docs.notte.cc, as configured in nottelabs/notte.
webfetch
MCP server "webfetch" as configured in firish/webfetch. Runs locally from the webfetch-llm@latest Python package.
nexus-browser-mcp
A local browser-control MCP server built with Playwright and an accessibility tree. Playwright is software for controlling web browsers, while an accessibility tree describes page elements in a way automation tools can inspect.
skyvern
AI-powered browser automation — navigate, click, fill forms, and extract data from any website. Remote server at api.skyvern.com.
membridge
Cross-platform, cross-process shared memory with rwlock and SPSC ring buffer for Python, powered by Rust. Runs locally from the membridge Python package.