Skip to content
MCP server

Flat Rate Math

Compare flat subscription, fixed bid and salaried hire by cost per request

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI
Runs
Locally
Version
0.1.1
Listing updated
2 days ago

About Flat Rate Math

Flat Rate Math is an open-source MCP server for finance and payments. It runs locally on your machine and is started by your AI client.

The server reduces three ways of paying for software work to one figure: total cost per delivered request. It ships as a single Python file using only the standard library and speaks JSON-RPC over stdio, answering initialize, ping, tools/list and tools/call.

The README's worked example puts an $84,000 fixed bid, an $18,290 per month hire and a $5,995 per month subscription side by side over 12 months and 30 requests. The subscription lane comes out at $2,398 per request, the bid at $2,800 and the hire at $7,316.

The flat-rate example is a real subscription from Poket Dev, whose founder wrote the server after redrawing the same spreadsheet for clients. Treat the numbers as a vendor-authored comparison.

Install

Run in a terminal

claude mcp add flatrate-math -- npx -y flatrate-math

Add to claude_desktop_config.json

{
  "mcpServers": {
    "flatrate-math": {
      "command": "npx",
      "args": [
        "-y",
        "flatrate-math"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "flatrate-math": {
      "command": "npx",
      "args": [
        "-y",
        "flatrate-math"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "flatrate-math": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "flatrate-math"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "flatrate-math": {
      "command": "npx",
      "args": [
        "-y",
        "flatrate-math"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "flatrate-math": {
      "command": "npx",
      "args": [
        "-y",
        "flatrate-math"
      ]
    }
  }
}

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

cost_per_request
Prices a single lane (bid, salary or flat) per delivered request.
compare_lanes
Ranks up to three lanes by cost per request.

What it does

Single-lane pricing
cost_per_request prices one lane from a mode, rate, duration and request count.
Three-lane ranking
compare_lanes ranks up to three lanes by cost per request.
Bid, salary and flat modes
Models a fixed bid, a fully loaded monthly hire and a monthly subscription.
No dependencies
One Python file with standard library only, MIT licensed.

Good for

  • Compare a development subscription against hiring
  • Sanity-check a fixed bid against monthly alternatives
  • Let an agent answer build-versus-buy cost questions
  • Reproduce a client's spreadsheet comparison on demand

Pricing

Open source

MIT licence; no paid plan mentioned

Prices change. Check poketdev.com before you buy.

Flat Rate Math FAQ

What inputs does it need?

A mode (bid, salary or flat), the dollar rate, how many months the work runs and the number of requests expected.

How do I run it?

Clone the repository and point your client at python3 server.py; nothing else is installed.

What licence applies?

MIT.

Is it tied to one vendor?

The example uses Poket Dev's subscription, but the rates are inputs you supply.

Is Flat Rate Math free?

Yes. Flat Rate Math is open source, so you can use and self-host it for free.

How do I add Flat Rate Math to Claude Code?

Run this command in your terminal: claude mcp add flatrate-math -- npx -y flatrate-math

What are the best alternatives to Flat Rate Math?

The closest alternatives to Flat Rate Math are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Flat Rate Math

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools