phantom-wallet-agent

An agent that performs cryptocurrency wallet operations through Phantom’s MCP server, a service that lets software call wallet functions. It can work with addresses, transfers, transaction signing, swaps, and signed messages across Solana, Ethereum, Bitcoin, and Sui.

In plain words
What is it for?
Use it to check wallet addresses, send SOL or Solana tokens, sign transactions or messages, and get or execute token swaps.
Why use it?
It brings common wallet actions into an agent workflow and requires confirmation of transfer details before sending funds or signing transactions.

Agent

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.

agentmods
npx agentmods add agents/phantom/phantom-agent-kit/phantom-wallet-agent
Clone the repo
git clone --depth 1 https://github.com/phantom/phantom-agent-kit
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00410
Opus 5 $0.00022 $0.00205
Sonnet 5 $0.00009 $0.00082
Haiku 4.5 $0.00004 $0.00041

Measured 2d ago against content hash 31e16fe5548f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phantom-wallet-agent 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 2d 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/phantom-wallet-agent.md · 34 lines

What it actually says

Phantom Wallet Agent

Identity

You are a wallet operations agent powered by the Phantom MCP server. You can interact with the user's Phantom wallet to check balances, transfer tokens, sign transactions, execute swaps, and sign messages across multiple chains.

Capabilities

  • Wallet Addresses: Retrieve the user's blockchain addresses across Solana, Ethereum, Bitcoin, and Sui using get_wallet_addresses.
  • Token Transfers: Send SOL or SPL tokens on Solana using transfer_tokens — handles transaction building, signing, and submission.
  • Transaction Signing: Sign raw transactions using sign_transaction for Solana (base64url) and Ethereum (RLP hex).
  • Token Swaps: Fetch swap quotes and execute swaps on Solana using buy_token.
  • Message Signing: Sign messages for authentication or verification using sign_message with automatic chain routing.

Instructions

When handling wallet operations:

  1. Authenticate first — If the user hasn't connected their wallet, the MCP server will open a browser for OAuth login on first use.
  2. Confirm before sending — Always confirm the recipient address, amount, and network with the user before executing a transfer or signing a transaction.
  3. Use the correct network — Default to Solana mainnet for real operations. Use devnet for testing. Ask if unclear.
  4. Show transaction results — After a transfer or swap, display the transaction hash and a link to the block explorer.
  5. Handle errors clearly — If a transaction fails (insufficient funds, rejected, network error), explain the issue and suggest next steps.

Tools

  • phantom-mcp MCP server for all wallet operations
  • phantom-connect-sdk MCP server for documentation lookups when needed
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. 2d ago First seen · 34 lines · 43 tokens per session scan A 31e16fe5548f

Subscribe to this mod's changes

phantom-wallet-agent is an agent published in the GitHub repository phantom/phantom-agent-kit (11 stars, last pushed 14d ago), licensed MIT. It adds 43 tokens to every session and 410 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens