mcpbeat

Cpfs MCP Server

io.github.JonahAlexanian/cpfs-mcp
local only

Cpfs MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 606 installs a week from npm.

CPFS Runner as an MCP server — deterministic AI coding guardrails via a compiled WASM core.

Installs per day peak 730 · avg 60 · -49% w/w
a month agotoday
606
Installs / week
npm · cpfs-mcp
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 cpfs-mcp -- npx -y cpfs-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "cpfs-mcp": {
      "args": [
        "-y",
        "cpfs-mcp"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.cpfs-mcp]
command = "npx"
args = ["-y", "cpfs-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "cpfs-mcp": {
      "args": [
        "-y",
        "cpfs-mcp"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "cpfs-mcp": {
      "args": [
        "-y",
        "cpfs-mcp"
      ],
      "command": "npx"
    }
  }
}

Cpfs MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Cpfs MCP?
Cpfs MCP 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 cpfs-mcp was installed 606 times last week.
How do I connect Cpfs MCP?
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 cpfs-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use Cpfs MCP?
The npm package cpfs-mcp was installed 606 times in the last week. Week over week that is -49%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.