mcpbeat

Flatland MCP Server

com.flatlandfi/flatland
local only

Flatland runs on your own machine — the client starts it, so there is no endpoint to ping. 64 installs a week from npm.

Financial reasoning infrastructure for AI agents: typed models, deterministic compilation, receipts

Installs per day peak 39 · avg 9 · +88% w/w
a month agotoday
64
Installs / week
npm · flatland-client
Stars
on GitHub
Last commit
0 releases in 90 days
License
language unknown

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add flatland -- npx -y flatland-client
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "flatland": {
      "args": [
        "-y",
        "flatland-client"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.flatland]
command = "npx"
args = ["-y", "flatland-client"]
.cursor/mcp.json
{
  "mcpServers": {
    "flatland": {
      "args": [
        "-y",
        "flatland-client"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "flatland": {
      "args": [
        "-y",
        "flatland-client"
      ],
      "command": "npx"
    }
  }
}

Flatland — questions

Answers built from our own checks of this server.

Why is there no uptime for Flatland?
Flatland runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package flatland-client was installed 64 times last week.
How do I connect Flatland?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls flatland-client straight from npm; nothing to host, nothing to sign up for.
How many people use Flatland?
The npm package flatland-client was installed 64 times in the last week. Week over week that is +88%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.