agentshield-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verify_contractA | 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. |
| scan_contractA | 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. |
| deep_scanA | 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. |
| monitor_walletA | 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. |
| freeze_walletA | 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. |
| get_alertsA | Get recent drain alerts and threat notifications for a wallet address. |
| get_statsA | Get AgentShield platform statistics: contracts verified, wallets monitored, threats blocked. |
| verify_batchA | Verify up to 50 contracts at once. Requires API key. Returns safety verdict for each contract in parallel. |
| register_webhookA | Register a webhook to receive alerts when a contract's ownership, proxy, or risk changes. Pro/Builder plan required. |
| get_dashboardB | View your API usage, billing, active webhooks, and alerts. Requires API key. |
| report_threatA | Report a malicious contract to the community. Earns +50 bonus API calls. 3+ reports auto-flag the contract. |
| get_reputationB | Get an agent's reputation score and tier (NEW, ACTIVE, VERIFIED, TRUSTED). Higher reputation = more benefits. |
| contract_diffA | Detect changes in a contract's ownership, proxy implementation, mint authority, taxes, or honeypot status since last check. Pro/Builder only. |
| create_referralA | Create a referral code. Both you and the redeemer get +500 free API calls. |
| redeem_referralA | Redeem a referral code for +500 free API calls. |
| get_leaderboardA | 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. |
| get_giveawayA | View the active giveaway, prizes, and past winners. Giveaway prizes are for paid subscribers only. |
| enter_giveawayA | Enter the active giveaway. PAID SUBSCRIBERS ONLY. Higher plans = more tickets (Builder 10x, Pro 5x, Starter 1x). |
| set_agent_nameA | Set your display name on the leaderboard. Requires API key. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
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.