io.github.meltingpixelsai/zero-core-budget
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Agent spending mgmt, budget tracking, ROI. Zero Core Budget.
| Author | io.github.meltingpixelsai |
|---|---|
| Access | mixed |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 163 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"zero-core-budget": {
"url": "https://budget.rugslayer.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (6)
list_toolsList all available Harvey Budget tools with pricing and input requirements. Use this for discovery.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
healthCheck Harvey Budget server status, uptime, and payment network configuration.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
register_agentRegister an agent with daily and weekly budget limits, or update them. The agent_id belongs to the wallet that pays for this call: call check_spend, report_spend and get_spending_report from the same wallet.
Parameters:
agent_id(required) — string — Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change itdaily_limit_usd(required) — number — Maximum daily spending in USDweekly_limit_usd(required) — number — Maximum weekly spending in USDcategory_limits— object — Optional per-category weekly limits (e.g. {security: 1.0, content: 2.0})
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
check_spendPre-spend budget approval check. Verifies daily/weekly/category limits, estimates ROI from your own past spends with this service, and suggests cheaper alternatives you have used. Call this BEFORE paying for any service.
Parameters:
agent_id(required) — string — Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it (register it first)service_id(required) — string — Service you want to pay for (e.g. 'harvey-tools/scrape_url')amount_usd(required) — number — Amount you're about to spend in USDcategory(required) — string — Spending category
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
report_spendRecord a completed spend with optional outcome tracking. Call this AFTER paying for a service to track spending and build ROI history.
Parameters:
agent_id(required) — string — Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change itservice_id(required) — string — Service that was usedamount_usd(required) — number — Amount spent in USDcategory(required) — string — Spending categoryvalue_received— string — Description of value receivedoutcome_success— boolean — Whether the service call succeeded
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_spending_reportDetailed spending analytics report. Returns total spent, category breakdown, top services with ROI, and optimization recommendations. Use to understand spending patterns and find inefficiencies.
Parameters:
agent_id(required) — string — Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change itperiod(required) — string — Report period
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.