Provides tools for verifying smart contracts, performing threat scans, monitoring wallets for drain detection, and accessing security intelligence on the Ethereum blockchain.
Provides tools for verifying smart contracts, performing threat scans, monitoring wallets for drain detection, and accessing security intelligence on the Optimism blockchain.
Provides tools for verifying smart contracts, performing threat scans, monitoring wallets for drain detection, and accessing security intelligence on the Polygon blockchain.
Provides tools for verifying smart contracts, performing threat scans, monitoring wallets for drain detection, and accessing security intelligence on the Solana blockchain.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agentshield-mcp verify contract 0x742d35Cc6634C0532925a3b844Bc4 on Ethereum"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Trust no contract. Verify before you transact.
Real-time smart contract security for autonomous AI agents. 19 MCP tools covering contract verification, wallet monitoring, drain detection, threat reporting, and competitive leaderboards. Supports Ethereum, Base, Polygon, Arbitrum, Optimism, BSC, Avalanche, and Solana.
npx agentshield-mcpRelated MCP server: aegis-defi
{
"mcpServers": {
"agentshield": {
"command": "npx",
"args": ["agentshield-mcp"]
}
}
}claude mcp add agentshield -- npx agentshield-mcpTool | Description |
| Quick safety check — honeypots, rug pulls, high taxes, hidden ownership. $0.001 via x402. |
| Full threat scan: 14+ checks including mint authority, freeze authority, proxy backdoors, liquidity traps, holder concentration. |
| Forensic analysis: bytecode patterns, ownership graph, exploit matching, risk breakdown. |
| Verify up to 50 contracts at once (API key required). |
| Compare two snapshots of a contract — detect proxy upgrades, permission changes. |
Tool | Description |
| Real-time drain detection. Fires webhook + auto-freezes all agent wallets on suspicious drop. |
| Emergency freeze all wallets for an agent. Stops transaction signing instantly. |
| Recent drain alerts and threat notifications for a wallet. |
Tool | Description |
| Report a malicious contract. 3+ reports auto-flag it. Earns +50 bonus API calls. |
| Community reputation score for any contract based on verified reports. |
| Get notified on proxy upgrades, ownership transfers, liquidity removal. |
| Your API usage, billing, active webhooks, and alerts. |
| Platform-wide stats: contracts verified, threats blocked, wallets monitored. |
Tool | Description |
| Race to 1M verifications. Free + paid users compete. Top 10 win $500 USDC. |
| Set your agent's display name on the leaderboard. |
| View active giveaways (paid subscribers only). |
| Enter a giveaway. Builder = 10x tickets, Pro = 5x, Starter = 1x. |
| Generate a referral code. Earn 20% commission on referrals. |
| Redeem a referral code for bonus API calls. |
AgentShield detects 14+ threat types:
Honeypot contracts (can buy, can't sell)
Rug pulls (liquidity removal patterns)
Hidden mint functions (infinite supply risk)
Freeze authority (owner can freeze your tokens)
Proxy backdoors (upgradeable to malicious code)
Tax manipulation (extreme buy/sell fees)
Blacklist functions (owner can block wallets)
Self-destruct capability
Hidden ownership transfers
External call exploits
Creator token concentration
Low/fake liquidity
Sell suppression patterns
Brand new unverified contracts
Ethereum, Base, Polygon, Arbitrum, Optimism, BSC, Avalanche, Solana
AgentShield uses x402 micropayments — pay per call, no signup required.
Tier | Price | Calls |
Free | $0 | 10 verify + 5 scan + 2 deep per day |
Pay-per-call | $0.001 | Unlimited (x402 USDC on Base or SOL) |
Starter | $4.99/mo | 5,000 calls |
Pro | $19.99/mo | 100,000 calls + unlimited deep scans + webhooks |
Builder | $49.99/mo | Unlimited everything |
Solana: 500 lamports to 7ci48VmgPTyEoqQCW2yb9HHEC8qDEK9gGbGoBV1GfHDf
Base USDC: $0.001 to 0x4BBc455ff6bA13682feC3b5F0261520b28C19e1c
npm install agentshield-jsimport { AgentShield } from 'agentshield-js';
const shield = new AgentShield();
const result = await shield.verify('0x...', 'ethereum');
if (result.is_honeypot) console.log('DANGER: Honeypot detected!');Full REST API at agentshield.win
MIT
Detect changes in a contract's ownership, proxy implementation, mint authority, taxes, or honeypot status since last check. Pro/Builder only.
Inputs: api_key (required), contract (required), chain.
Create a referral code. Both you and the redeemer get +500 free API calls.
Inputs: api_key (required).
Deep forensic analysis: ownership, permissions, exploit pattern matching, bytecode analysis, and risk breakdown. Goes deeper than verify or scan. 2 free/day, unlimited for Pro/Builder subscribers.
Inputs: contract (required), chain.
Enter the active giveaway. PAID SUBSCRIBERS ONLY. Higher plans = more tickets (Builder 10x, Pro 5x, Starter 1x).
Inputs: api_key (required), agent_name.
Emergency freeze all monitored wallets for a wallet address or agent. Stops all transaction signing until manually unfrozen. Requires API key (X-Agent-Key) or wallet ownership.
Inputs: reason, wallet, api_key, agent_id.
Get recent drain alerts and threat notifications for a wallet address.
Inputs: wallet (required), limit.
View your API usage, billing, active webhooks, and alerts. Requires API key.
Inputs: api_key (required).
View the active giveaway, prizes, and past winners. Giveaway prizes are for paid subscribers only.
Inputs: no named parameters.
View the competitive agent leaderboard — race to 1M verifications. Everyone competes (free + paid). Top agents win prizes. Filter by category: total, verifications, scans, reports, streak.
Inputs: api_key, category.
Get an agent's reputation score and tier (NEW, ACTIVE, VERIFIED, TRUSTED). Higher reputation = more benefits.
Inputs: agent, api_key.
Get AgentShield platform statistics: contracts verified, wallets monitored, threats blocked.
Inputs: no named parameters.
Watch a wallet for drain threats. When balance drops beyond threshold in a single transaction, fires an alert to your callback URL and auto-freezes all linked agent wallets.
Inputs: wallet (required), callback_url (required), chains, agent_id, +1 more.
Redeem a referral code for +500 free API calls.
Inputs: code (required), api_key (required).
Register a webhook to receive alerts when a contract's ownership, proxy, or risk changes. Pro/Builder plan required.
Inputs: api_key (required), contract (required), callback_url (required), chain, +1 more.
Report a malicious contract to the community. Earns +50 bonus API calls. 3+ reports auto-flag the contract.
Inputs: reason (required), contract (required), chain, api_key, +1 more.
Full threat detection scan: honeypots, rug pulls, mint authority, freeze authority, proxy backdoors, tax manipulation, blacklist functions, liquidity analysis, and holder concentration. 14+ checks in under 2 seconds. Use this before trading any token.
Inputs: contract (required), chain.
Set your display name on the leaderboard. Requires API key.
Inputs: name (required), api_key (required).
Verify up to 50 contracts at once. Requires API key. Returns safety verdict for each contract in parallel.
Inputs: api_key (required), contracts (required), chain.
Verify a smart contract for security risks before transacting. Detects honeypots, rug pulls, high taxes, hidden ownership, and other threats. Costs $0.001 via x402 micropayment (USDC on Base or SOL). Always call this before approving any on-chain transaction.
Inputs: contract (required), chain, payment.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 19 tools
The scanning tools (verify_contract, scan_contract, deep_scan) have clear tiering but still overlap in purpose, which could cause an agent to pick the wrong one. Other tools like get_alerts, get_stats, and get_dashboard are distinct. Overall, most tools have clearly differentiated roles.
Tool names mix verb-first (get_alerts, verify_contract, monitor_wallet) with noun-first (contract_diff) and adverb forms (deep_scan). The inconsistent use of get_ for reads but not for other actions makes naming unpredictable.
At 19 tools, the set is on the heavier side, including gamification features (referrals, leaderboard, giveaways) that are tangential to the core security mission. Still, the core security tools are well-scoped, so the count is not excessive.
Coverage is solid for scanning, verification, and wallet monitoring, but missing an unfreeze tool creates a dead end after freeze_wallet. Webhook management is minimal (register only), and there is no way to view or manage monitored wallets directly.
Read-only smart-contract security intelligence for autonomous agents.
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
Crypto security, honeypot detection, wallet analysis, and token risk scoring across 31 blockchains.
Security intelligence for AI agents monitoring Ethereum before actions.