- Home
- Skills
- APIs & Backend
- steward mcp
steward mcp
Enable AI agents to browse products and execute pay-per-call USDC transactions on Base via x402.
Free
Works with the AI Agents you already use
steward mcp
Example session with this skill installed
List the products available in the catalog and check how much I've spent today using the spend meter.
- Read your context and instructions
- Compiled the steward mcp
I have retrieved the current product catalog and checked your local spend meter for this session.
Catalog and Spend Status
| Product Name | Category | Price (USDC) | Description |
|---|---|---|---|
| API Search | Tooling | 0.02 | High-speed web search via x402 endpoint |
| LLM Inference | AI | 0.05 | Access to fine-tuned Llama 3 models |
| Image Gen | Media | 0.10 | Stable Diffusion image generation per call |
| Data Fetch | Research | 0.01 | Direct extraction from verified news sources |
Current Spend Summary
- Daily Spend: 0.00 USDC
- Session Limit: 5.00 USDC
- Status: Within limits
Next steps
- Select a product from the list above to generate a payment quote.
- Use
steward_get_quoteto start the transaction flow for a specific item. - Review the reward tier status if you plan to make multiple purchases.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing payments between AI agents and services is currently manual and friction-heavy. This skill enables agents to autonomously browse catalogs, get quotes, and execute pay-per-call transactions using the x402 protocol.
What it does
- x402 payment core handles the full transaction lifecycle including fetching quotes, verifying signatures, and submitting signed payments.
- Product discovery allows agents to browse the product catalog and retrieve specific purchase instructions.
- Spend tracking provides a local spend meter tool for agents to monitor their session expenditures against defined caps.
- Rewards integration fetches information on loyalty tiers and standard 10-15% reward rates.
How it works
- The agent uses discovery tools to find products or services in the catalog.
- It requests a quote for a specific action to receive the x402 payment requirements.
- The user or wallet signs the transaction based on the quote provided.
- The agent submits the signed proof to finalize the payment and access the service.
Frameworks & tools
This skill uses the Model Context Protocol (MCP) over stdio and targets USDC transactions on the Base network. It is built for Node.js environments.
Why this beats prompting it yourself
Writing manual logic for the x402 quote-verify-sign flow is error-prone and risks session timeouts or lost payments. This skill encapsulates the entire state machine, ensuring agents track their own spending and follow the protocol specifications exactly.
Use cases
- Automate micro-payments for agent-to-agent service calls.
- Track daily spending limits for autonomous agents.
- Verify payment signatures before fulfilling digital orders.
- Browse and buy digital assets through the x402 economy.
Known limitations
Transactions are limited to USDC on the Base network. Requires a Node.js runtime version 20 or higher and an MCP-compatible client.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 11 days ago
- Free to download with an account
Requires