ToolTrust
C42/100
zhizhuodemao

js-reverse-mcp

mcp4.0.1

@zhizhuodemao

AI Agent-first JS 逆向 MCP Server:有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测,可选 CloakBrowser。

By zhizhuodemao | 86 findings | Scanned 7/31/2026 | tooltrust-scanner/v0.3.19 | 2.4k

11 Critical6 High21 Low48 Info

Risk Summary

Needs Approval

Excessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (86)

  • CriticalAS-006

    💻Arbitrary Code Execution ×11

    heuristic signal

    tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

    break_on_xhrclick_elementevaluate_scriptget_paused_infoget_request_initiatorget_script_sourcelist_scriptssearch_in_sourcesselect_frameset_breakpoint_on_textstep

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

  • HighAS-003

    🔀Scope Mismatch ×6

    tool name "get_paused_info" implies read-only operation but declares exec permission

    get_paused_info

    tool name "get_request_initiator" implies read-only operation but declares exec permission

    get_request_initiator

    tool name "get_script_source" implies read-only operation but declares exec permission

    get_script_source

    tool name "list_breakpoints" implies read-only operation but declares exec permission

    list_breakpoints

    tool name "list_scripts" implies read-only operation but declares exec permission

    list_scripts

    tool name "search_in_sources" implies read-only operation but declares exec permission

    search_in_sources

    Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×21

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    break_on_xhrclear_network_requestsclear_site_dataevaluate_scriptget_paused_infoget_request_initiatorget_script_sourceget_websocket_messageslist_breakpointslist_console_messageslist_network_requestslist_scriptspause_or_resumeremove_breakpointsave_script_sourcesearch_in_sourcesselect_frameselect_pageset_breakpoint_on_textsteptake_screenshot

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-002

    ⚠️Excessive Permissions ×24

    declared capabilities: code/command execution, network access

    break_on_xhrget_script_sourcelist_scriptssearch_in_sources

    declared capabilities: network access

    clear_network_requestsclear_site_datalist_console_messagesnew_pageselect_page

    declared capabilities: code/command execution

    click_elementget_paused_infopause_or_resume

    declared capabilities: code/command execution, network access, filesystem access

    evaluate_scriptsave_script_source

    declared capabilities: code/command execution, network access, HTTP requests

    get_request_initiatorlist_breakpointsset_breakpoint_on_text

    declared capabilities: network access, filesystem access

    get_websocket_messagesremove_breakpointtake_screenshot

    declared capabilities: network access, filesystem access, HTTP requests

    list_network_requests

    declared capabilities: network access, HTTP requests

    navigate_page

    declared capabilities: code/command execution, HTTP requests

    select_frame

    declared capabilities: code/command execution, filesystem access

    step

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×24

    No metadata.dependencies or repo_url were exposed by this MCP server, and no local project manifest could be inferred from the launch command.

    break_on_xhrclear_network_requestsclear_site_dataclick_elementevaluate_scriptget_paused_infoget_request_initiatorget_script_sourceget_websocket_messageslist_breakpointslist_console_messageslist_network_requestslist_scriptsnavigate_pagenew_pagepause_or_resumeremove_breakpointsave_script_sourcesearch_in_sourcesselect_frameselect_pageset_breakpoint_on_textsteptake_screenshot

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y js-reverse-mcp"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)