Skip to content
Agentmart
Submit a tool

MCP Browser

Browser automation using the user's Chromium session — JS execution, auth, and anti-bot support.

Connector by cherchyk · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 9
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/cherchyk-mcpbrowser

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Browser automation using the user's Chromium session — JS execution, auth, and anti-bot support.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
5 read · 7 write · 2 delete
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 14

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • browser_detect_forms
  • browser_fetch_webpage
  • browser_get_current_html
  • browser_plugin_info
  • browser_take_screenshot

Write 7 · Create, change, send or run things.

  • accept_eula
  • browser_click_element
  • browser_navigate_history
  • browser_plugin_action
  • browser_scroll_page
  • browser_type_text
  • compose_email

Delete 2 · Delete, drop, revoke or wipe things.

  • browser_close_tab
  • browser_execute_javascript

Network hosts it talks to 8

  • calendar.google.com · found in code
  • dashboard.corp.com · found in code
  • eng.ms · found in code
  • github.com · found in code
  • login.com · found in code
  • mail.google.com · found in code
  • portal.azure.com · found in code
  • word.cloud.microsoft · found in code

Files it touches

  • /opt/brave.com/brave/brave-browser
  • /opt/microsoft/msedge/msedge
  • /proc/version
  • %LOCALAPPDATA%
  • Your home directory (~)

Tools (14)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • accept_eula

    CRITICAL: You MUST ask the user 'Do you accept the MCPBrowser EULA?' and wait for their explicit 'Yes' response BEFORE calling this tool. Set userExplicitlyConfirmed=true ONLY if the user explicitly said 'Yes' or 'I accept'. If the user has not responded or said 'No', DO NOT call this tool. Calling this tool without user consent violates the EULA terms.

  • browser_click_elementClick Element

    Click buttons, links, or any element on a browser-loaded page. Use when: you need to navigate a website, submit a form, press a button, follow a link, or interact with any clickable UI element. Targets by CSS selector or visible text. Returns updated page HTML after click. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_close_tabClose Tabcan change or delete data

    Close a browser tab to free resources. Use when: you are done with a page and want to release memory, or need to reset session state for a hostname. Uses exact hostname match.

  • browser_detect_formsDetect Formsread-only

    Scan a browser-loaded page and return all forms as structured JSON — fields, types, validation rules, submit buttons, and orphaned inputs. Use when: you need to understand a form before filling it, discover what fields exist on a page, or map form structure for automation. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_execute_javascriptExecute JavaScriptcan change or delete data

    Run JavaScript on a browser-loaded page and get the result. Use when: you need to extract structured data from a page, manipulate the DOM, read page state, run custom queries on page content, or perform UI actions that CSS selectors cannot reach. Returns the script result as JSON, text, or void. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_fetch_webpageFetch Web Pageread-only

    Load any URL and return its content using a real browser with full JavaScript execution. Use whenever a webpage needs to be loaded — whether to read content, interact with a web app, or access any HTTP/HTTPS resource. Connects to the user's existing browser session with all cookies, logins, and SSO sessions available automatically. Handles JavaScript rendering, authentication, and anti-bot protection. Prefer this over generic HTTP fetch for authenticated or JS-heavy pages.

  • browser_get_current_htmlGet Current HTMLread-only

    Re-read HTML from an already-loaded page without reloading it. Use when: you need to check page state after a click or form fill, re-extract content from the current page, or get updated HTML after dynamic changes. Much faster than browser_fetch_webpage since it skips navigation. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_navigate_historyNavigate Back/Forward

    Go back or forward in browser history. Use when: you clicked a link and need to return to the previous page, or want to go forward after going back. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_plugin_actionPlugin Action

    Execute a site-specific plugin action on an already-open matching browser tab. Call browser_plugin_info first to discover available plugins and their actions, and use browser_fetch_webpage first when no matching site is open.

  • browser_plugin_infoPlugin Inforead-only

    List available site-specific plugins and their actions. Use when: browser_fetch_webpage suggests a plugin in nextSteps, or you want to check what optimized actions are available for the current site. Call with no arguments to list all plugins, or with a plugin name for details.

  • browser_scroll_pageScroll Page

    Scroll within a browser-loaded page. Automatically detects scrollable containers inside SPAs (e.g., ADO, Jira, Gmail) where the main content scrolls inside an inner div rather than the window. Use when: you need to see more content below the fold, bring an element into view before clicking, scroll to a specific section, or navigate long pages. Supports scroll by direction, to a CSS selector, or to absolute coordinates. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_take_screenshotTake Screenshotread-only

    Capture a screenshot of a browser-loaded page as PNG. Set fullPage=true to capture the entire scrollable page in one shot — this avoids multiple scroll+screenshot cycles. Only use fullPage=false when you specifically need just the current viewport (rare). Use when: you need to see what a page looks like, analyze visual layout, view charts/images/graphs, debug UI issues, or when HTML alone is insufficient. Returns base64-encoded PNG. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • browser_type_textType Text

    Type text into input fields on a browser-loaded page. Use when: you need to fill a form, enter a search query, type into a text box, or input data into any editable field. Supports filling multiple fields in a single call. PREREQUISITE: Page must be loaded with browser_fetch_webpage first.

  • compose_email

    Open Gmail compose window via keyboard shortcut and fill in email fields

Signals

Stars
9
Forks
1
Open issues
1
Last commit (this folder)
Oct 12, 2026 (16 days ago)
Last release
Oct 12, 2026 (16 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.cherchyk/mcpbrowser
Version
0.4.6
Auth
No auth
Packages
npm mcpbrowser
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 25, 2026

More from cherchyk

Cite this page

MCP Browser. Agent Mart. https://agentmart.dev/connectors/cherchyk-mcpbrowser (last updated 2026-10-25)