PluginBench
MCP Server

io.github.JonahAlexanian/cpfs-mcp MCP Server

io.github.JonahAlexanian/cpfs-mcp

Registry
How to choose

What this kind of tool is for

  • Automate a build, test, or deployment step you repeat by hand.
  • Review or refactor code in an existing repository without leaving your agent.
  • Bridge an internal service or CLI into the agent toolset.

How to compare servers like this

Scope of control:
Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
Environment fit:
Match the runtime it expects (Node, Python, a container) to what you actually run.
Maintenance signal:
Check the last-commit date — dev tooling that lags upstream breaks first.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.JonahAlexanian/cpfs-mcp MCP server?

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

How to install io.github.JonahAlexanian/cpfs-mcp

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • CPFS_WORKSPACE

    Absolute path to the workspace root CPFS will manage (defaults to the current working directory)

  • CPFS_DASHBOARD_PORT

    Port for the CPFS dashboard web UI (defaults to 8765)

  • CPFS_DEBUG

    Set to '1' to enable verbose debug logging

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "cpfs-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "cpfs-mcp"
      ],
      "env": {
        "CPFS_WORKSPACE": "<YOUR_CPFS_WORKSPACE>",
        "CPFS_DASHBOARD_PORT": "<YOUR_CPFS_DASHBOARD_PORT>",
        "CPFS_DEBUG": "<YOUR_CPFS_DEBUG>"
      }
    }
  }
}

Related MCP servers

APApple Files logo

Inspect and manage local files and folders on macOS with AI assistance.

9
Python
MIT
View repository →

Vectorize images to SVG and export to PDF, EPS, DXF, PNG, JPG, or WEBP via Vectorise.Me.

View repository →

Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.

Physical Layer Linter: validates RF and radar calculations against hard physical limits.

1
Python
MIT
View repository →

Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.

2
TypeScript
Apache-2.0
View repository →

Trust & reliability data for x402 endpoints before your agent pays them.

0
TypeScript
MIT
View repository →