MCP.so
Sign In
R

Readedit

@abnersajr

Repository

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

3

Read a file and optionally edit it in one call. For single-file tasks, use this instead of separate read_file + edit calls. Returns file content. Edit params (old_string, new_string) are optional — omit them for read-only.

Edit multiple files when you already have their contents in context. ALWAYS use this instead of multiple separate edit calls. Each edit uses exact string or regex replacement. For read+edit combos, use multi_read_edit instead.

Read and optionally edit multiple files in one call. ALWAYS batch multi-file operations here instead of separate read_file/edit calls. Read-only ops return file content. Edit ops return compact results by default (no content) to save tokens — set include_content=true to get post-edit content, include_original=true for diffing.

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

Basic information

Category

Other

Transports

stdio

Author

abnersajr

Submitted by

Abner Soares Alves jr

More Other MCP servers

🪟 Windows-MCP

CursorTouch

MCP Server for Computer Use in Windows

6.3K

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Inbox Zero AI

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

IDA Pro MCP

mrexodia

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

9.9K

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3