mcpbeat Sign in

Fantoma MCP Server

local only

Fantoma runs on your own machine — the client starts it, so there is no endpoint to ping. 580 installs a week from pypi. Last commit 13 Oct 2026.

Accessibility-tree browser for AI agents: read pages, log in, extract data, run tasks.

Installs per day peak 458 · avg 56 · +73% w/w
a month agotoday
580
Installs / week
pypi · fantoma
7
Stars
0 open issues
13 Oct 2026
Last commit
from GitHub
MIT
License
Python

What the code does

We read the source, 1 d ago · rules ccca72095570

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

                trace_path = os.path.join(self._trace_dir, f"{domain}-{ts}.zip")
        self._base_url = f"https://api.telegram.org/bot{bot_token}"

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add fantoma -- uvx fantoma
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "fantoma": {
      "args": [
        "fantoma"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.fantoma]
command = "uvx"
args = ["fantoma"]
.cursor/mcp.json
{
  "mcpServers": {
    "fantoma": {
      "args": [
        "fantoma"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "fantoma": {
      "args": [
        "fantoma"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Fantoma

same job, measured the same way
Browsegrab
by arknill

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

109 installs/wk local only
Fortress
by tiliondev

Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.

473 installs/wk local only
MCP Browser Research
by infoinlet-marketplace

Web browsing & research for AI agents — fetch/read pages, structured extraction, Exa search.

38 installs/wk local only
browser-buddy
by hahahahahahahahah6

Let AI coding agents read pages through your real, logged-in Chrome browser.

134 installs/wk local only
D
Dropcoin A11y
by freshfos

Accessibility pre-checks (WCAG/BFSG) in a real browser + statement drafts. Pay per call.

2 tools answering
Anchor Browser
by anchorbrowser

Cloud browsers for AI agents: get past bot detection, sign in with MFA, run web tasks at scale.

answering
A11yScope
by perceivable

WCAG 2.2 AA accessibility checks for pages and HTML, run locally in headless Chrome.

1 028 installs/wk local only
Yab, Yet Another Browser
by yetanotherbrowser

Your own signed-in Mac browser for any agent: open, read and act in tabs. Local and free.

773 installs/wk local only

Fantoma — questions

Answers built from our own checks of this server.

Why is there no uptime for Fantoma?
Fantoma runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package fantoma was installed 580 times last week.
How do I connect Fantoma?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls fantoma straight from pypi; nothing to host, nothing to sign up for.
How many people use Fantoma?
The pypi package fantoma was installed 580 times in the last week. Week over week that is +73%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Fantoma open source?
Yes — it is published under the MIT licence, written in Python and 7 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.