Koskamo

Harvey Budget MCP

An MCP server for AI agents that provides budget tracking, spend approval workflows, ROI analysis, and intelligent spending recommendations. It operates on a pure logic basis without LLM dependency and utilizes x402 micropayments in USDC for access.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Harvey Budget MCP logo, by MeltingPixelsCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by MeltingPixels
You need:no account needed
MCP endpoint (Streamable HTTP)
https://budget.rugslayer.com/mcp
Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (6)

6 of 6 have a description · 0 of 6 declare behavior hints · 4 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Register an agent with specific budget limits
  • Check if a proposed spend is within the allocated budget
  • Record a spend event with its outcome
  • Generate spending analytics with ROI and recommendations

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.meltingpixelsai/zero-core-budget@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
harvey-budget 1.0.0
MCP protocol negotiated in check
2025-06-18
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

6 advertised

list_tools
Advertised by the server during the last successful anonymous check.

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

list_tools input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "additionalProperties": false
}
health
Advertised by the server during the last successful anonymous check.

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

health input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {},
  "additionalProperties": false
}
register_agent
Advertised by the server during the last successful anonymous check.

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.

register_agent input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "agent_id",
    "daily_limit_usd",
    "weekly_limit_usd"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it"
    },
    "category_limits": {
      "type": "object",
      "description": "Optional per-category weekly limits (e.g. {security: 1.0, content: 2.0})",
      "additionalProperties": {
        "type": "number"
      }
    },
    "daily_limit_usd": {
      "type": "number",
      "maximum": 10000,
      "minimum": 0.001,
      "description": "Maximum daily spending in USD"
    },
    "weekly_limit_usd": {
      "type": "number",
      "maximum": 100000,
      "minimum": 0.001,
      "description": "Maximum weekly spending in USD"
    }
  },
  "additionalProperties": false
}
register_agent annotations
{
  "paymentHint": true,
  "paymentVersion": 1,
  "paymentNetworks": [
    {
      "type": "svm",
      "asset": {
        "address": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
        "decimals": 6
      },
      "network": "solana",
      "recipient": "2CkpGoj5cGYdmxSBZYC21AJia9hGjj5bKzCTkyrPzL4H",
      "maxAmountRequired": "1000"
    }
  ],
  "paymentPriceUSD": "$0.001"
}
check_spend
Advertised by the server during the last successful anonymous check.

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.

check_spend input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "agent_id",
    "service_id",
    "amount_usd",
    "category"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "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)"
    },
    "category": {
      "enum": [
        "security",
        "trading",
        "social",
        "content",
        "data",
        "infrastructure",
        "other"
      ],
      "type": "string",
      "description": "Spending category"
    },
    "amount_usd": {
      "type": "number",
      "minimum": 0,
      "description": "Amount you're about to spend in USD"
    },
    "service_id": {
      "type": "string",
      "description": "Service you want to pay for (e.g. 'harvey-tools/scrape_url')"
    }
  },
  "additionalProperties": false
}
check_spend annotations
{
  "paymentHint": true,
  "paymentVersion": 1,
  "paymentNetworks": [
    {
      "type": "svm",
      "asset": {
        "address": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
        "decimals": 6
      },
      "network": "solana",
      "recipient": "2CkpGoj5cGYdmxSBZYC21AJia9hGjj5bKzCTkyrPzL4H",
      "maxAmountRequired": "1000"
    }
  ],
  "paymentPriceUSD": "$0.001"
}
report_spend
Advertised by the server during the last successful anonymous check.

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

report_spend input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "agent_id",
    "service_id",
    "amount_usd",
    "category"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it"
    },
    "category": {
      "enum": [
        "security",
        "trading",
        "social",
        "content",
        "data",
        "infrastructure",
        "other"
      ],
      "type": "string",
      "description": "Spending category"
    },
    "amount_usd": {
      "type": "number",
      "minimum": 0,
      "description": "Amount spent in USD"
    },
    "service_id": {
      "type": "string",
      "description": "Service that was used"
    },
    "value_received": {
      "type": "string",
      "description": "Description of value received"
    },
    "outcome_success": {
      "type": "boolean",
      "description": "Whether the service call succeeded"
    }
  },
  "additionalProperties": false
}
report_spend annotations
{
  "paymentHint": true,
  "paymentVersion": 1,
  "paymentNetworks": [
    {
      "type": "svm",
      "asset": {
        "address": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
        "decimals": 6
      },
      "network": "solana",
      "recipient": "2CkpGoj5cGYdmxSBZYC21AJia9hGjj5bKzCTkyrPzL4H",
      "maxAmountRequired": "1000"
    }
  ],
  "paymentPriceUSD": "$0.001"
}
get_spending_report
Advertised by the server during the last successful anonymous check.

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

get_spending_report input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "agent_id",
    "period"
  ],
  "properties": {
    "period": {
      "enum": [
        "day",
        "week",
        "month"
      ],
      "type": "string",
      "description": "Report period"
    },
    "agent_id": {
      "type": "string",
      "description": "Your agent's name. It belongs to the wallet you pay from: only calls paid from that wallet can read or change it"
    }
  },
  "additionalProperties": false
}
get_spending_report annotations
{
  "paymentHint": true,
  "paymentVersion": 1,
  "paymentNetworks": [
    {
      "type": "svm",
      "asset": {
        "address": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
        "decimals": 6
      },
      "network": "solana",
      "recipient": "2CkpGoj5cGYdmxSBZYC21AJia9hGjj5bKzCTkyrPzL4H",
      "maxAmountRequired": "5000"
    }
  ],
  "paymentPriceUSD": "$0.005"
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
777 ms
95th percentile latency
777 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 777 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http harvey-budget-mcp https://budget.rugslayer.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add harvey-budget-mcp --url https://budget.rugslayer.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable harvey-budget-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "harvey-budget-mcp": {
      "url": "https://budget.rugslayer.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "harvey-budget-mcp": {
      "type": "streamableHttp",
      "url": "https://budget.rugslayer.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start harvey-budget-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "harvey-budget-mcp": {
      "type": "http",
      "url": "https://budget.rugslayer.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http harvey-budget-mcp https://budget.rugslayer.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://budget.rugslayer.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "harvey-budget-mcp": {
      "serverUrl": "https://budget.rugslayer.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Harvey Budget MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,161