Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.soulfir/babelwrap-mcp

PYPI · BABELWRAP-MCP · SCANNED SEP 20

Let AI agents interact with any website through natural language instead of CSS selectors

Available components

0 this week 82 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 23 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
Schema Quality & AI Usability81
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1375 tokens (~76/item across 18 items; 18 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the io.github.soulfir/babelwrap-mcp server?

io.github.soulfir/babelwrap-mcp runs locally as a PyPI package, launched with uvx babelwrap-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · babelwrap-mcp

# add to Claude Code
claude mcp add soulfir-babelwrap-mcp -- uvx babelwrap-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "soulfir-babelwrap-mcp": {
      "command": "uvx",
      "args": [
        "babelwrap-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "soulfir-babelwrap-mcp": {
      "command": "uvx",
      "args": [
        "babelwrap-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add soulfir-babelwrap-mcp -- uvx babelwrap-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "soulfir-babelwrap-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "babelwrap-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add soulfir-babelwrap-mcp --command uvx --arg babelwrap-mcp
# ~/.hermes/config.yaml
mcp_servers:
  soulfir-babelwrap-mcp:
    command: "uvx"
    args: ["babelwrap-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "soulfir-babelwrap-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "babelwrap-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add soulfir-babelwrap-mcp -t stdio -c uvx -a babelwrap-mcp
// mcp.json
{
  "mcpServers": {
    "soulfir-babelwrap-mcp": {
      "command": "uvx",
      "args": [
        "babelwrap-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/babelwrap-mcp@0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 23 packages
Packages resolved 23
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 18 exposed · ~1,375 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
babelwrap_back ~45

Navigate back in the browser history.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_click ~112

Click an element on the page using a natural language description.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.
targetstringyesNatural language description of the element to click (e.g. "the Login button", "first search result"). TIP: Pass an element ID from a previous snapshot (e.g. "btn-login", "input-email") to bypass LLM…

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_close_session ~31

Close and clean up a browser session.

NameTypeReqDescription
session_idstringyesThe session ID to close.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_extract ~76

Extract structured data from the current page using a natural language query.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
querystringyesNatural language description of what data to extract (e.g. "all product names and prices").
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_fill ~110

Fill an input field with a value.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.
targetstringyesNatural language description of the input field (e.g. "Email address field"). TIP: Pass an element ID from a previous snapshot (e.g. "input-email") to bypass LLM resolution entirely for instant, dete…
valuestringyesThe value to fill in.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_forward ~45

Navigate forward in the browser history.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_hover ~84

Hover over an element on the page.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.
targetstringyesNatural language description of the element to hover over. TIP: Pass an element ID from a previous snapshot to bypass LLM resolution entirely for instant, deterministic targeting.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_list_pages ~62

List all open pages (tabs/popups) in this browser session. Use this to discover tabs opened by popups or target="_blank" links, then switch to them with babelwrap_switch_page.

NameTypeReqDescription
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_navigate ~64

Navigate to a URL and get a structured snapshot of the page.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.
urlstringyesThe URL to navigate to.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_new_session ~31

Create a new browser session for web interaction.

NameTypeReqDescription
metadataOptional labels or tags for this session.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_press ~74

Press a keyboard key on the current page.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
keystringyesThe key to press (e.g. "Enter", "Tab", "Escape", "ArrowDown").
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_screenshot ~50

Take a screenshot of the current page (for debugging).

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_scroll ~95

Scroll the page up or down.

NameTypeReqDescription
amountstring"page" (full viewport), "half" (half viewport), or pixel count as string (default: "page").
compactbooleanIf True, return a compact snapshot with minimal whitespace.
directionstring"up" or "down" (default: "down").
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_snapshot ~52

Get the current page state as a structured snapshot without taking any action.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_submit ~99

Submit a form on the current page.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
session_idstringyesThe active session ID.
targetOptional natural language description of which form to submit. If omitted, submits the most prominent form. TIP: Pass an element ID from a previous snapshot (e.g. "btn-submit") to bypass LLM resoluti…

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_switch_page ~87

Switch to a different page (tab/popup) within this session. Use babelwrap_list_pages first to see available pages and their indices.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with reduced token usage.
indexintegeryesThe page index to switch to (from babelwrap_list_pages).
session_idstringyesThe active session ID.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_upload ~116

Upload a file to a file input element on the page.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
file_base64stringyesBase64-encoded file content.
filenamestringyesThe filename to use for the upload.
session_idstringyesThe active session ID.
targetstringyesNatural language description of the file input element. TIP: Pass an element ID from a previous snapshot to bypass LLM resolution entirely for instant, deterministic targeting.

Structured output declared, but exposes no named fields.

No examples provided.

babelwrap_wait_for ~142

Wait for a condition on the page before proceeding. Useful after clicking a button that triggers async loading, SPA navigation, or any action where you need to wait for specific content to appear.

NameTypeReqDescription
compactbooleanIf True, return a compact snapshot with minimal whitespace.
selectorWait until this CSS selector matches a visible element.
session_idstringyesThe active session ID.
textWait until this text appears on the page.
timeout_msintegerMaximum time to wait in milliseconds (default: 10000, max: 30000).
url_containsWait until the URL contains this string.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the io.github.soulfir/babelwrap-mcp server?

io.github.soulfir/babelwrap-mcp is listed in the public MCP registry as io.github.soulfir/babelwrap-mcp. Let AI agents interact with any website through natural language instead of CSS selectors. This page covers its PyPI package (babelwrap-mcp).

Is the io.github.soulfir/babelwrap-mcp server safe to use?

io.github.soulfir/babelwrap-mcp scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.soulfir/babelwrap-mcp server expose?

io.github.soulfir/babelwrap-mcp exposes 18 tools: babelwrap_new_session, babelwrap_close_session, babelwrap_navigate, babelwrap_snapshot, babelwrap_click, and 13 more. Their descriptions and schemas cost roughly 1,375 tokens of context every time the server is loaded.

Is the io.github.soulfir/babelwrap-mcp server still maintained?

io.github.soulfir/babelwrap-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.