Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AgentForge -- DeFi Safety Toolkit (Solana + EVM, x402)

    1

    DeFi safety layer for agents providing rug checks, transaction decoding, and contract audits on EVM and Solana.

    Free

    11 usesSecurity scanned
    AgentForge -- DeFi Safety Toolkit (Solana + EVM, x402)

    AgentForge -- DeFi Safety Toolkit (Solana + EVM, x402)

    Example session with this skill installed

    **Check this Solana token for rug risks:** 7xKX... and explain what the next transaction does: 4n3a...

    • Read your context and instructions
    • Compiled the agentforge -- defi

    **Risk Scan:** High. Mint authority is enabled. Top 5 holders own 85% of supply. **Transaction Summary:** This call swaps 5.0 SOL for 12,500 TOKEN via Raydium. Max slippage 0.5%. Status: Safe to simulate.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Gives your agent 20 DeFi safety tools: token risk scans (mint/freeze authority, holder concentration, liquidity depth), real transaction simulation, tx decoding, wallet approval audits, and contract docs across Solana and 5 EVM chains. Free tools work with zero setup (program lookup, contract registry, full MCP server access); advanced endpoints are pay-per-use via x402 USDC micropayments — no API keys, no accounts, prices from $0.05, all disclosed upfront in the skill.

    EVM label registry is limited to 384 contracts. Paid endpoints require x402-aware infrastructure or MCP tools for USDC payments.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    11 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 months ago

    • Free with an Agensi account

    Requires

    Vercel
    Python
    Payments MCP

    Permissions

    Network Access

    Allowed Hosts

    agentforge-taupe.vercel.app
    Listed4 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    The toolkit helps agents identify common DeFi risks such as honeypots, rug pulls, hidden mint functions, and liquidity locks across Solana and five major EVM chains. Any agent with this skill can simulate transactions and perform deep contract audits before executing a trade.

    This skill is built on the Model Context Protocol (MCP), making it natively compatible with any agent platform or IDE that supports MCP servers (like Claude Desktop or Windsurf) as well as custom-built AI agents with internet access.

    The basic tools and contract registry are free to use with zero setup; advanced security scans use x402 USDC micropayments, meaning you only pay a few cents per request directly through your agent's wallet with no API keys or subscriptions required.

    No, the toolkit supports both Solana and legacy EVM chains (Ethereum, Base, Arbitrum, etc.), allowing your agent to monitor token safety and decode transactions across multiple ecosystems using a single interface.

    Yes, the AgentForge team regularly updates the contract registry and risk detection logic to capture new exploit patterns; these updates are pushed server-side, so your agent always has access to the latest security definitions.

    New in Web3 & Crypto