ToolTrust
C27/100
Smithery

web3auth-integrate

mcpsmithery

@Smithery

MetaMask Embedded Wallets MCP (formerly Web3Auth) gives AI coding assistants live access to Embedded Wallets documentation, SDK references, integration examples, and community troubleshooting. MetaMask Embedded Wallets is not a wallet app itself, but embedded wallet infrastructure that helps developers add non-custodial Web3 wallets to web, mobile, and gaming apps using familiar login methods like Google, GitHub, email, SMS, and other OAuth or passwordless flows. This MCP server is built for real integration work. It lets agents search docs, fetch full documentation pages, retrieve complete example code, inspect SDK types and hooks, and surface real-world implementation issues. It is especially useful for tasks like choosing the right SDK, implementing social login, understanding key derivation behavior, avoiding wallet address changes caused by auth or configuration mistakes, and debugging framework-specific issues across React, Next.js, Flutter, React Native, and other platforms. Use it when you want an AI assistant to generate or review MetaMask Embedded Wallets integrations using current source material instead of stale model memory. Pair it with the MetaMask Embedded Wallets Skill for best results: the skill teaches the assistant how to reason about architecture, authentication, SDK selection, and common pitfalls, while this MCP server provides up-to-date docs, examples, SDK references, and implementation details.

By Smithery | 18 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13

5 High2 Medium6 Low5 Info

Risk Summary

Needs Approval

Excessive Permissions plus Missing Rate Limits 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 (18)

  • HighAS-002

    ⚠️Excessive Permissions ×5

    tool declares network permission

    search_docsget_docget_exampleget_sdk_referencesearch_community

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

  • MediumAS-002

    ⚠️Excessive Permissions ×2

    tool declares fs permission

    get_example

    tool declares db permission

    search_community

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

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×5

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

    search_docsget_docget_exampleget_sdk_referencesearch_community

    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.

  • LowAS-002

    ⚠️Excessive Permissions

    get_example:tool declares http permission

    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 ×5

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    search_docsget_docget_exampleget_sdk_referencesearch_community

    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 web3auth-integrate"

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)