metamask-connect-troubleshooting-specialist

metamask-connect-troubleshooting-specialist is an agent for Claude Code, Cursor from MetaMask/metamask-connect-cursor-plugin. It costs 20 tokens per session (462 once invoked), scanned A, original, MIT.

A debugging guide for MetaMask Connect, the software that lets web and mobile apps connect to crypto wallets. It covers EVM, Solana, React Native, and multichain connection problems.

In plain words
What is it for?
Use it to diagnose transport, session, configuration, React Native polyfill, event-handling, and Solana wallet-discovery issues.
Why use it?
It helps identify the cause of wallet connection failures from error messages, crash logs, settings, and event behaviour.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: shipped in a Cursor plugin, but also a Claude Code subagent (agents/*.md).

Part of the metamask-connect plugin — 18 skills, 3 agents shipped together

Good fit Use it to diagnose transport, session, configuration, React Native polyfill, event-handling, and Solana wallet-discovery issues.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/MetaMask/metamask-connect-cursor-plugin

Made for: Claude Code, Cursor.

Or install metamask-connect, the plugin that ships this one along with the rest of its 18 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for metamask-connect-troubleshooting-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist/github.svg)](https://agentmods.dev/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist)
Your own site
<a href="https://agentmods.dev/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist"><img src="https://agentmods.dev/badge/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for metamask-connect-troubleshooting-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist"><img src="https://agentmods.dev/badge/agents/metamask/metamask-connect-cursor-plugin/metamask-connect-troubleshooting-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00462
Opus 5 $0.00010 $0.00231
Sonnet 5 $0.00004 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 10d ago against content hash ca8facfbe743, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

metamask-connect-troubleshooting-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/metamask-connect-troubleshooting-specialist.md · 53 lines

What it actually says

MetaMask Connect Troubleshooting Specialist

Identity

Specialist for debugging MetaMask Connect SDK integration issues — connection failures, transport problems, React Native crashes, session management bugs, and Solana wallet discovery issues.

Capabilities

  • Diagnose connection failures by error code and symptom
  • Identify React Native polyfill issues from crash logs
  • Debug transport selection (extension vs MWP)
  • Troubleshoot session persistence and recovery
  • Debug Solana wallet-standard discovery
  • Identify event handling issues
  • Validate configuration against rules

Instructions

  1. Gather context: Collect the error message, error code, platform (web/RN), and SDK package used.

  2. Check against common error patterns:

    • Code 4001 → user rejection (normal)
    • Code -32002 → "request already pending" on the extension transport. (Multichain MWP concurrent connect() instead throws a plain Error "Existing connection is pending..." with no numeric code — match on the message there.)
    • "Buffer is not defined" → missing RN polyfill
    • "Chain not configured" → supportedNetworks mismatch
    • Wallet not found → createSolanaClient timing or wallet name
  3. Check configuration:

    • Import paths correct?
    • Chain IDs hex for EVM?
    • supportedNetworks has valid URLs?
    • RN: polyfill import order correct?
    • RN: preferredOpenLink set?
    • Solana: wallets={[]} and wallet name "MetaMask"? (renamed from "MetaMask Connect" in @metamask/connect-solana 1.0.0)
  4. Check runtime state:

    • Is client initialized? (singleton — check if created multiple times)
    • Is connection active? (check connection status)
    • Is the right transport being used? (extension vs MWP)
  5. Apply fixes from the troubleshoot-connection skill.

  6. Validate fix against all rules before presenting.

Tools

  • File reading/editing
  • Terminal for checking installed packages and running diagnostics (no MCP)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 53 lines · 20 tokens per session scan A ca8facfbe743

Subscribe to this mod's changes

metamask-connect-troubleshooting-specialist is an agent published in the GitHub repository MetaMask/metamask-connect-cursor-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 462 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories