x402-agent-tollbooth
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | API key for Gemini, required to run the server. |
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 | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| contract.auditA | Live Smart Contract AI Auditor. Analyzes Base contracts for vulnerabilities. Requires 1.00 USDC payment via x402 protocol. |
| contract.patchA | Premium Smart Contract Patcher. Not only audits but rewrites vulnerable Solidity code into production-ready safe code. Requires 5.00 USDC payment via x402 protocol. |
| llm.queryA | Agent-to-Agent Compute Arbitrage. Route raw LLM prompts to our Gemini instance. Requires 0.10 USDC micro-transaction via x402 protocol. |
| wallet.profileA | Smart Money Oracle. Analyzes a wallet's on-chain behavior and assigns a psychological risk profile. Requires 2.00 USDC payment via x402 protocol. |
| memory.storeB | Agent Memory Bank: Store arbitrary context, snippets, or vectors persistently. Requires 0.01 USDC micro-transaction. |
| memory.retrieveB | Agent Memory Bank: Retrieve stored context or data. Requires 0.01 USDC micro-transaction. |
| contract.auditTeaserA | Free teaser for the smart contract auditor. Returns vulnerability counts but obscures details to upsell the paid audit. Free to use. |
| market.alphaA | Purchase aggregated intelligence on which contracts and wallets other AI agents are analyzing right now. Requires 10.00 USDC. |
| token.analyzeA | Premium real-time liquidity, volume, and smart-money analytics for any token on Base. Required payment: 0.50 USDC. |
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 9 tools
Most tools target distinct resources (llm, wallet, memory, market, token), but the contract.audit / contract.patch / contract.auditTeaser cluster overlaps heavily: patch includes auditing, and auditTeaser is an explicitly degraded version of audit, so an agent may struggle to pick between them.
Nearly all tools follow a clean namespace.action pattern (llm.query, contract.audit, wallet.profile, memory.store), with only contract.auditTeaser breaking the convention by cramming a modifier into the verb slot instead of using a separate action.
Nine tools is well within the ideal 3-15 range, and each represents a discrete paid service rather than a redundant wrapper, so the set feels appropriately scoped.
Memory has store/retrieve but no update/delete, and there is no discovery, pricing, or payment/balance tool despite the whole server being an x402 tollbooth, leaving notable lifecycle gaps agents must work around.