MCP.so
Sign In
R

Readedit

@abnersajr

About Readedit

MCP server that combines Read+Edit file operations into single tool calls. 80-95% fewer tool calls formulti-file refactoring across Claude, Cursor, Windsurf, and more.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "readedit": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-readedit"
      ]
    }
  }
}

Tools

4

Read a file, optionally edit it — 1 call instead of 2

Edit multiple files at once

Read + optionally edit multiple files — the powerhouse

Show your token savings statistics

Overview

What is Readedit?

Readedit is an MCP server that gives AI coding assistants batch file operations, combining read and edit into single tool calls to reduce round-trips. It is designed for developers using Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Continue, or Zed who want faster, token-efficient multi-file refactoring.

How to use Readedit?

Run directly with npx mcp-readedit (no install needed) or install globally with npm install -g mcp-readedit. Add the server configuration to your MCP client’s settings (e.g., Claude Desktop JSON config, Claude Code CLI, Cursor .cursor/mcp.json, Windsurf Settings, Cline MCP Servers, Continue .continue/config.yaml, or Zed settings.json). Four tools are available: read_edit, multi_edit, multi_read_edit, and get_gain.

Key features of Readedit

  • Collapses read+edit pairs into single tool calls
  • Edits multiple files in one call with multi_edit
  • Reads+edits multiple files with multi_read_edit
  • Provides token savings statistics via get_gain
  • Tracks gains in a local SQLite database
  • Supports regex, replace-all, line offset, and limit options

Use cases of Readedit

  • Refactoring across many files without separate read-then-edit calls
  • Batch editing multiple files simultaneously with a single tool call
  • Reading file contents with the option to edit in the same call
  • Monitoring token savings from using combined operations

FAQ from Readedit

What makes Readedit different from using separate Read/Edit tools?

It reduces tool calls by 80–95% for multi-file refactoring because one ReadEdit call replaces a read-then-edit pair.

What runtime dependencies does Readedit require?

Node.js 20 or later (LTS recommended). No other runtime dependencies are required.

Where are token savings statistics stored?

In a local SQLite database that auto-creates on first use. The database tracks each tool call and estimates tokens saved (~200 per avoided call).

Can I see my savings without starting the MCP server?

Yes. If installed globally, run readedit gain in the terminal for summary, daily, recent, or all breakdowns (JSON export available).

How do I make my AI assistant prefer ReadEdit tools automatically?

Add the provided instructions block to your project’s CLAUDE.md, AGENTS.md, .cursorrules, or globally in ~/.claude/AGENTS.md.

Frequently asked questions

What makes Readedit different from using separate Read/Edit tools?

It reduces tool calls by 80–95% for multi-file refactoring because one ReadEdit call replaces a read-then-edit pair.

What runtime dependencies does Readedit require?

Node.js 20 or later (LTS recommended). No other runtime dependencies are required.

Where are token savings statistics stored?

In a local SQLite database that auto-creates on first use. The database tracks each tool call and estimates tokens saved (~200 per avoided call).

Can I see my savings without starting the MCP server?

Yes. If installed globally, run `readedit gain` in the terminal for summary, daily, recent, or all breakdowns (JSON export available).

How do I make my AI assistant prefer ReadEdit tools automatically?

Add the provided instructions block to your project’s `CLAUDE.md`, `AGENTS.md`, `.cursorrules`, or globally in `~/.claude/AGENTS.md`.

Comments

More Other MCP servers