What is selenium-mcp AGENTS.md?

Repository instructions for an MCP server that exposes Selenium WebDriver to AI agents. Selenium is a tool for controlling web browsers; the instructions cover the TypeScript project structure, build checks, unit tests, and end-to-end tests in headless Chrome.

Use them to install dependencies, type-check and build the server, run unit tests, run browser tests, and find the code for browser sessions and tools.

They tell the coding agent how this browser-automation project is organised and which checks to run. They also distinguish tests that need Chrome from those that do not.

How gaforov/selenium-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to gaforov/selenium-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/gaforov/selenium-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/gaforov/selenium-mcp

Made for: Codex, OpenCode.

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/gaforov/selenium-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/gaforov/selenium-mcp/agents-md)

Your own site

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

Per session 1,571 This file is loaded in full into every session.

When invoked 1,571 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	$0.01571	$0.01571
Opus 5.5	$0.00628	$0.00628
Sonnet 5.5	$0.00314	$0.00314
Haiku 4.5	$0.00157	$0.00157

Measured 1mo ago against content hash 292be40a2a5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

selenium-mcp AGENTS.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 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.

AGENTS.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding assistants (and humans) changing this repository. For end-user docs, see README.md and docs/.

What this is

A Model Context Protocol server that exposes Selenium WebDriver to AI agents over stdio. TypeScript (strict, ESM), Node.js 20+, @modelcontextprotocol/sdk (McpServer.registerTool), and zod v4 (import from "zod/v4").

Commands

npm install
npm run typecheck   # tsc --noEmit
npm run build       # compile to dist/
npm test            # build + unit tests (test/*.test.mjs), no browser needed
npm run test:e2e    # build + end-to-end tests in headless Chrome (Chrome must be installed)
npm run dev         # run the server from source with tsx

Tests import from dist/, so they always build first. Run all three checks before finishing: npm run typecheck && npm test && npm run test:e2e.

File map

Path	What lives there
`src/server.ts`	Entry point: CLI flags (`--help`, `--version`, `--list-tools`), stdio transport, shutdown. The version comes from `package.json` at runtime.
`src/driver/driverManager.ts`	Browser sessions (single and multi-session) and which one is active.
`src/tools/index.ts`	Registers every tool. `CORE_TOOL_NAMES` must list exactly the registered tools; an E2E test fails if they drift.
`src/tools/<tool>.ts`	One file per tool, or per tight family (`assertions`, `cookies`, `session`, `selectorHints`).
`src/tools/shared/`	Reusable pieces: `selector.ts` (selector schema, `timeoutMs`), `targetSelector.ts` (selector-or-ref), `waits.ts`, `pageRefs.ts` (`capture_page` refs), `selectorHints.ts` (hint storage), and logic shared with `batch_execute` (`selectOption.ts`, `pageWaits.ts`).
`src/resources/index.ts`	MCP resources `browser-status://current` and `accessibility://current`.
`src/utils/`	`toolResult.ts` (`textResult`, `errorResult`, `toErrorMessage`) and optional tracing.
`test/*.test.mjs`	Unit tests, including `toolDescriptions.test.mjs`.
`test/e2e/`	End-to-end tests grouped by feature; `helpers/harness.mjs` provides `useBrowserSession()`.
`test/fixtures/`	Local HTML pages the E2E tests drive, served over HTTP.

Read the full file on GitHub · 107 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.

1mo ago First seen · 107 lines · 1,571 tokens per session scan A 292be40a2a5d

Subscribe to this mod's changes

selenium-mcp AGENTS.md is an instructions file published in the GitHub repository gaforov/selenium-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,571 tokens to every session, about $0.0063 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 2026-09-14.

Browser automation Languages TypeScript ai-agents browser-automation claude cursor mcp mcp-server

selenium-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
selenium-mcp AGENTS.mdgaforov/selenium-mcp	Instructions file	0	1mo ago	MIT	A	1,571	Codex, OpenCode
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

selenium-mcp: Instructions file for Codex