MCP.Market

SideButton MCP Server

by sidebutton·io.github.sidebutton/sidebutton·v1.5.2·5 stars
No reviews yet

Open-source MCP server with browser automation and knowledge packs for AI agents

B72/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B72/100

full report

Adoption
Growing

5 stars44 downloads/wk

Reviews

Write one

Nobody has reviewed SideButton MCP Server yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

SideButton MCP Server tools (28, 7 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • browser_batchwrite action

    Run a SEQUENCE of browser actions in ONE call instead of one round trip per action. Each step is the same shape you would pass to the individual tool, plus a "cmd" field naming which tool to run. A batch is a DETERMINISTIC run: actions you already know the selectors for, executed top to bottom, halting at the first failure (unless on_error:"continue"). By default it ends by returning a fresh acces

  • capture_page

    Capture selectors and interactive elements from the current page.

  • clear_basic_authwrite action

    Remove stored HTTP Basic Auth credentials. Omit "origin" to clear all stored credentials; pass "origin" to clear just that site.

  • click

    Click an element on the page.

  • evaluatewrite action

    Execute JavaScript in the browser page context and return the result. Useful for reading page state, checking values, or performing calculations.

  • exists

    Check if an element exists on the page. Returns true/false without throwing. Useful for conditional logic.

  • extract

    Extract text content from an element.

  • extract_all

    Extract text from all elements matching a selector, joined by a separator. Useful for getting lists of items, table columns, or repeated elements.

  • extract_map

    Extract structured data from repeated elements. For each element matching the outer selector, extracts named fields using sub-selectors. Returns JSON array of objects.

  • fill

    Fill a form field by setting its value programmatically. Unlike "type" (which simulates keystrokes), "fill" sets the value directly and triggers React/Vue/Angular change events. Use this for framework-controlled inputs where "type" doesn't work.

  • get_browser_status

    Check if the browser extension is connected.

  • get_run_logwrite action

    Retrieve the execution log for a completed workflow run.

  • get_workflow

    Get detailed information about a specific workflow.

  • hover

    Hover over an element (positions cursor for scroll targeting).

  • list_run_logswrite action

    List recent workflow execution logs.

  • list_workflows

    List all available workflow automations.

  • navigate

    Navigate the connected browser tab to a URL.

  • press_key

    Press a key on the keyboard. Use this for keyboard shortcuts, Tab navigation, Enter, Escape, arrow keys, etc. Supports key combinations like "Ctrl+A" or "Shift+Tab".

  • publish_artifactwrite action

    Publish a piece of evidence (a screenshot, a design mockup, an RCA/coverage report) to the portal RIGHT NOW, mid-session, and get back a paste-ready snippet to cite in your ONE resolution comment on the ticket. The file is uploaded, attached to the ticket automatically, and given a tokenized no-login download link \u2014 the snippet contains that link plus the Jira inline-attachment reference. Use

  • run_workflowwrite action

    Execute a workflow automation by ID. Returns a run_id for tracking execution status.

  • screenshot

    Capture a screenshot of the current page. Prefer cropping to a specific area instead of capturing the full viewport \u2014 use ref (from snapshot), selector (CSS), or region (manual rect) to save context tokens. Full viewport is fine for first visit to a new page; after that, crop to the relevant section.

  • scroll

    Scroll the page.

  • scroll_into_view

    Scroll a specific element into the viewport. More precise than "scroll" \u2014 targets an exact element.

  • select_option

    Select an option from a native <select> dropdown element. Use this instead of click for <select> elements, as native dropdowns cannot be controlled via click events.

  • set_basic_auth

    Provide HTTP Basic Auth credentials so the browser logs in silently instead of showing the native username/password modal, which would otherwise block the page and hang automation. Applies to the connected tab. Omit "origin" to use the credentials for any site that challenges; pass "origin" (e.g. "https://staging.example.com") to scope them to one site. When a challenge has no matching credentials

  • snapshot

    Capture accessibility snapshot of the current page. Returns YAML with element refs for use with click/type. Use includeContent=true to also include visible text content as markdown. Note: taking a snapshot may dismiss inline modals or popups \u2014 use screenshot instead if you need to verify modal content.

  • type

    Type text into an input element.

  • wait

    Wait for an element to appear on the page. Blocks until the element matching the selector exists in the DOM, or throws after timeout.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

1 high
  • Code scan34 source files scanned13/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    dist/cli.js: …=== "win32" ? "start" : "xdg-open"; exec(`${openCmd} "${deviceData.verification_uri_complete}"`)…
Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How SideButton MCP Server compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
72/100
higher than 38% of 866 Scraping and browsing servers
Tools
28
the typical Scraping and browsing server has 6
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
5
more than 73% of 583 Scraping and browsing servers
Downloads a week
44
more than 28% of 309 Scraping and browsing servers with a package

What its tools let an agent do: 20 read · 5 change · 1 send or post · 2 run or deploy

Install SideButton MCP Server in Claude Code, Cursor or VS Code

Runs npx -y @sidebutton/server on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add sidebutton -- npx -y @sidebutton/server
Add to Cursor

What the publisher says

From the SideButton MCP Server repository's README, as published. We do not edit it. Read it on GitHub

SideButton

Open-source AI agent platform for agentic coding — MCP server, knowledge packs, and AI workflow automation.

sidebutton.com · docs.sidebutton.com

Run AI coding agents with agentic workflows, knowledge packs, and real browser control. Connect Claude Code, Codex, Cursor, ChatGPT, or any MCP client.

npx sidebutton@latest
# Dashboard at http://localhost:9876

What you get

Quick Start

# Install and start
npx sidebutton@latest

# Or from source
pnpm install && pnpm build && pnpm start

# Open http://localhost:9876

CLI

pnpm cli serve          # Start server with dashboard
pnpm cli serve --stdio  # Start with stdio transport (for Claude Desktop)
pnpm cli list           # List available workflows
pnpm cli status         # Check server status

# Skill pack management
pnpm cli registry add <path|url>   # Install skill packs from a registry
pnpm cli registry update [name]    # Update installed packs
pnpm cli registry remove <name>    # Uninstall packs and remove registry
pnpm cli search [query]            # Search available skill packs

# Creating skill packs
pnpm cli init [domain]             # Scaffold a new skill pack
pnpm cli validate [path]           # Validate pack structure
pnpm cli publish [source]          # Publish to a registry

MCP Server

SideButton is an open-source MCP server for AI coding agents. Agents connect to it directly for browser control, workflow automation, and domain knowledge.

Works with Claude Code, Codex, Cursor, Claude Desktop, VS Code, Windsurf, ChatGPT — any MCP client.

Claude Code

claude mcp add sidebutton --transport http http://localhost:9876/mcp

Persists to ~/.claude.json; add --scope project to write ./.mcp.json instead. Full guide: Claude Code SideButton MCP setup.

Codex

Add to ~/.codex/config.toml:

[mcp_servers.sidebutton]
command = "sidebutton"
args = ["serve", "--stdio"]

Full guide: OpenAI Codex SideButton MCP setup.

Claude Desktop

Add to ~/Library/Application Support/Claude/claudedesktopconfig.json:

{
  "mcpServers": {
    "sidebutton": {
      "command": "npx",
      "args": ["sidebutton", "--stdio"]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "sidebutton": {
      "url": "http://localhost:9876/mcp"
    }
  }
}

MCP Tools

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

SideButton MCP Server: common questions

Is SideButton MCP Server safe?
Mostly: it is graded B (72/100). Read the SideButton MCP Server safety report
How do I install SideButton MCP Server?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does SideButton MCP Server need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is SideButton MCP Server maintained?
The last commit was 43 days ago (2026-09-22). The latest release is v1.5.2.
What can I use instead of SideButton MCP Server?
Servers from other publishers that do the same job: GrowBlocks Dev Kit MCP server, SeleniumBase MCP server and Next AI Draw.io MCP server.
How does SideButton MCP Server compare with other Scraping and browsing MCP servers?
safety score 72/100 (higher than 38% of 866 Scraping and browsing servers); tools 28 (the typical Scraping and browsing server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to SideButton MCP Server

Same job from other publishers: the closest match first, then the best rated.

  • GrowBlocks Dev Kit
    Build, play-test with screenshots, and ship three.js browser games on GrowBlocks.
    A
  • SeleniumBase MCP
    Stealthy browser automation, testing, and web-scraping via CDP Mode.
    A
  • Next AI Draw.io
    draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
    A
  • AIHawk
    AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
    More from feder-cr →
    A
  • Browser
    MCP server for browser use access
    B