meltingpixelsai avatar

Zero Core Budget

meltingpixelsai/harvey-budget

This connects your Claude environment to RelayZero's agent economy infrastructure, exposing budget preflight checks, x402 payment rail settlement, and ROI tracking across autonomous agent spending. You get tools to query daily budgets, block or warn before transactions hit Solana, and pull normalized receipts from USDC settlements in the arena, task marketplace, and intelligence feed. Reach for this when you're building agents that need to operate within spend limits or justify their service purchases with auditable proof. The streamable HTTP transport hits budget.rugslayer.com/mcp and surfaces the same preflight verdicts and rail receipts that power RelayZero's 8-game arena and task economy. Think of it as a spending governor with teeth, not just logging.

tools
6
transport
HTTP
last updated
Apr 30, 2026

Install

From registry metadata
$ npx add-mcp https://budget.rugslayer.com/mcp --name zero-core-budget

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http zero-core-budget https://budget.rugslayer.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 6 tools

Verified live against the running server on Nov 6, 2026.

list_toolsList all available Harvey Budget tools with pricing and input requirements. Use this for discovery.

List all available Harvey Budget tools with pricing and input requirements. Use this for discovery.

No parameters. Call it with no arguments.

healthCheck Harvey Budget server status, uptime, and payment network configuration.

Check Harvey Budget server status, uptime, and payment network configuration.

No parameters. Call it with no arguments.

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.4 params

Register 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* required
agent_id*string
Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it
category_limitsobject
Optional per-category weekly limits (e.g. {security: 1.0, content: 2.0})
daily_limit_usd*number
Maximum daily spending in USD
weekly_limit_usd*number
Maximum weekly spending in USD
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.4 params

Pre-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* required
agent_id*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)
amount_usd*number
Amount you're about to spend in USD
category*string
Spending categoryone of security · trading · social · content · data · infrastructure
service_id*string
Service you want to pay for (e.g. 'harvey-tools/scrape_url')
report_spendRecord a completed spend with optional outcome tracking. Call this AFTER paying for a service to track spending and build ROI history.6 params

Record a completed spend with optional outcome tracking. Call this AFTER paying for a service to track spending and build ROI history.

Parameters* required
agent_id*string
Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it
amount_usd*number
Amount spent in USD
category*string
Spending categoryone of security · trading · social · content · data · infrastructure
outcome_successboolean
Whether the service call succeeded
service_id*string
Service that was used
value_receivedstring
Description of value received
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.2 params

Detailed spending analytics report. Returns total spent, category breakdown, top services with ROI, and optimization recommendations. Use to understand spending patterns and find inefficiencies.

Parameters* required
agent_id*string
Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it
period*string
Report periodone of day · week · month

Sponsors

Readme

Details

Repository
github.com/meltingpixelsai/harvey-budget
Website
relayzero.ai
Category
AI & LLM Tools
Package
@meltingpixels/zero-core-budget
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from meltingpixelsai

Related AI & LLM Tools MCP servers

View all
1michu5696 avatarAgora402io.github.michu5696/agora402Escrow protection for agent payments on Base — USDC held in smart contract until job completion.0stars
2michu5696 avatarPaycrowio.github.michu5696/paycrowEscrow protection for agent payments on Base — USDC held in smart contract until job completion.0stars
3migmediamarketing-ai avatarNoto Crmmigmediamarketing-ai/noto-crm-mcp-serverMinimalist CRM with AI agent for freelancers — pricing, features, comparisons0stars
4modelbound avatarModelbound Mcpmodelbound/modelbound-mcp-serverLocal-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.0stars
5flipcoin-fun avatarFlipcoinflipcoin-fun/flipcoin-mcpAgent-first prediction markets on Base. Trade, quote, create markets via MCP.0stars
6mukundakatta avatarRagmetric Mcpmukundakatta/mcp-stackRAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.0stars